{ "best_metric": 0.848845249619693, "best_model_checkpoint": "./results/checkpoint-12204", "epoch": 3.0, "eval_steps": 500, "global_step": 12204, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0024582104228121925, "grad_norm": 4.467207908630371, "learning_rate": 2.9975417895771878e-05, "loss": 1.4158, "step": 10 }, { "epoch": 0.004916420845624385, "grad_norm": 3.8742997646331787, "learning_rate": 2.9950835791543758e-05, "loss": 1.1938, "step": 20 }, { "epoch": 0.007374631268436578, "grad_norm": 3.0423967838287354, "learning_rate": 2.9926253687315632e-05, "loss": 1.066, "step": 30 }, { "epoch": 0.00983284169124877, "grad_norm": 5.9557785987854, "learning_rate": 2.9901671583087512e-05, "loss": 0.874, "step": 40 }, { "epoch": 0.012291052114060964, "grad_norm": 10.07143783569336, "learning_rate": 2.987708947885939e-05, "loss": 1.0172, "step": 50 }, { "epoch": 0.014749262536873156, "grad_norm": 4.170281410217285, "learning_rate": 2.985250737463127e-05, "loss": 0.938, "step": 60 }, { "epoch": 0.01720747295968535, "grad_norm": 4.032867431640625, "learning_rate": 2.9827925270403147e-05, "loss": 0.9112, "step": 70 }, { "epoch": 0.01966568338249754, "grad_norm": 4.253580093383789, "learning_rate": 2.9803343166175024e-05, "loss": 1.0215, "step": 80 }, { "epoch": 0.022123893805309734, "grad_norm": 9.525086402893066, "learning_rate": 2.97787610619469e-05, "loss": 0.893, "step": 90 }, { "epoch": 0.024582104228121928, "grad_norm": 5.15816593170166, "learning_rate": 2.975417895771878e-05, "loss": 1.0037, "step": 100 }, { "epoch": 0.02704031465093412, "grad_norm": 7.5928955078125, "learning_rate": 2.972959685349066e-05, "loss": 0.8992, "step": 110 }, { "epoch": 0.029498525073746312, "grad_norm": 5.754878044128418, "learning_rate": 2.970501474926254e-05, "loss": 0.9152, "step": 120 }, { "epoch": 0.0319567354965585, "grad_norm": 6.063644886016846, "learning_rate": 2.9680432645034416e-05, "loss": 1.0039, "step": 130 }, { "epoch": 0.0344149459193707, "grad_norm": 5.603899002075195, "learning_rate": 2.9655850540806293e-05, "loss": 1.0436, "step": 140 }, { "epoch": 0.03687315634218289, "grad_norm": 11.509993553161621, "learning_rate": 2.963126843657817e-05, "loss": 0.8831, "step": 150 }, { "epoch": 0.03933136676499508, "grad_norm": 6.53792142868042, "learning_rate": 2.960668633235005e-05, "loss": 0.9845, "step": 160 }, { "epoch": 0.04178957718780728, "grad_norm": 4.272523880004883, "learning_rate": 2.9582104228121928e-05, "loss": 0.85, "step": 170 }, { "epoch": 0.04424778761061947, "grad_norm": 6.995558738708496, "learning_rate": 2.9557522123893808e-05, "loss": 0.8746, "step": 180 }, { "epoch": 0.04670599803343166, "grad_norm": 5.718236923217773, "learning_rate": 2.953294001966568e-05, "loss": 0.8441, "step": 190 }, { "epoch": 0.049164208456243856, "grad_norm": 6.290430068969727, "learning_rate": 2.9508357915437562e-05, "loss": 0.8652, "step": 200 }, { "epoch": 0.051622418879056046, "grad_norm": 9.633130073547363, "learning_rate": 2.948377581120944e-05, "loss": 0.8715, "step": 210 }, { "epoch": 0.05408062930186824, "grad_norm": 3.5873327255249023, "learning_rate": 2.945919370698132e-05, "loss": 0.6982, "step": 220 }, { "epoch": 0.056538839724680434, "grad_norm": 6.801671981811523, "learning_rate": 2.9434611602753197e-05, "loss": 0.9069, "step": 230 }, { "epoch": 0.058997050147492625, "grad_norm": 6.924914360046387, "learning_rate": 2.9410029498525074e-05, "loss": 0.8559, "step": 240 }, { "epoch": 0.061455260570304815, "grad_norm": 6.925126552581787, "learning_rate": 2.938544739429695e-05, "loss": 0.7404, "step": 250 }, { "epoch": 0.063913470993117, "grad_norm": 7.1232805252075195, "learning_rate": 2.936086529006883e-05, "loss": 0.742, "step": 260 }, { "epoch": 0.06637168141592921, "grad_norm": 3.57456636428833, "learning_rate": 2.9336283185840708e-05, "loss": 0.7643, "step": 270 }, { "epoch": 0.0688298918387414, "grad_norm": 9.64212417602539, "learning_rate": 2.931170108161259e-05, "loss": 0.8214, "step": 280 }, { "epoch": 0.07128810226155359, "grad_norm": 7.229945182800293, "learning_rate": 2.9287118977384462e-05, "loss": 0.7479, "step": 290 }, { "epoch": 0.07374631268436578, "grad_norm": 11.38809585571289, "learning_rate": 2.9262536873156343e-05, "loss": 0.783, "step": 300 }, { "epoch": 0.07620452310717797, "grad_norm": 2.950946569442749, "learning_rate": 2.923795476892822e-05, "loss": 0.6675, "step": 310 }, { "epoch": 0.07866273352999016, "grad_norm": 4.499948501586914, "learning_rate": 2.92133726647001e-05, "loss": 0.827, "step": 320 }, { "epoch": 0.08112094395280237, "grad_norm": 4.844608783721924, "learning_rate": 2.9188790560471977e-05, "loss": 0.7167, "step": 330 }, { "epoch": 0.08357915437561456, "grad_norm": 5.256041526794434, "learning_rate": 2.9164208456243854e-05, "loss": 0.8049, "step": 340 }, { "epoch": 0.08603736479842675, "grad_norm": 16.993913650512695, "learning_rate": 2.913962635201573e-05, "loss": 0.6795, "step": 350 }, { "epoch": 0.08849557522123894, "grad_norm": 9.650567054748535, "learning_rate": 2.9115044247787612e-05, "loss": 0.7631, "step": 360 }, { "epoch": 0.09095378564405113, "grad_norm": 5.803030014038086, "learning_rate": 2.909046214355949e-05, "loss": 0.7239, "step": 370 }, { "epoch": 0.09341199606686332, "grad_norm": 8.228071212768555, "learning_rate": 2.906588003933137e-05, "loss": 0.7284, "step": 380 }, { "epoch": 0.09587020648967552, "grad_norm": 8.895597457885742, "learning_rate": 2.9041297935103246e-05, "loss": 0.7964, "step": 390 }, { "epoch": 0.09832841691248771, "grad_norm": 9.865562438964844, "learning_rate": 2.9016715830875124e-05, "loss": 0.6626, "step": 400 }, { "epoch": 0.1007866273352999, "grad_norm": 17.60503578186035, "learning_rate": 2.8992133726647e-05, "loss": 0.6816, "step": 410 }, { "epoch": 0.10324483775811209, "grad_norm": 9.900540351867676, "learning_rate": 2.896755162241888e-05, "loss": 0.622, "step": 420 }, { "epoch": 0.10570304818092428, "grad_norm": 3.804746389389038, "learning_rate": 2.8942969518190758e-05, "loss": 0.7758, "step": 430 }, { "epoch": 0.10816125860373647, "grad_norm": 10.85200023651123, "learning_rate": 2.891838741396264e-05, "loss": 0.6398, "step": 440 }, { "epoch": 0.11061946902654868, "grad_norm": 5.919342994689941, "learning_rate": 2.8893805309734512e-05, "loss": 0.7733, "step": 450 }, { "epoch": 0.11307767944936087, "grad_norm": 3.195143938064575, "learning_rate": 2.8869223205506393e-05, "loss": 0.6992, "step": 460 }, { "epoch": 0.11553588987217306, "grad_norm": 12.408628463745117, "learning_rate": 2.884464110127827e-05, "loss": 0.7051, "step": 470 }, { "epoch": 0.11799410029498525, "grad_norm": 6.432305812835693, "learning_rate": 2.882005899705015e-05, "loss": 0.6432, "step": 480 }, { "epoch": 0.12045231071779744, "grad_norm": 9.975807189941406, "learning_rate": 2.8795476892822027e-05, "loss": 0.7022, "step": 490 }, { "epoch": 0.12291052114060963, "grad_norm": 7.012577533721924, "learning_rate": 2.8770894788593904e-05, "loss": 0.838, "step": 500 }, { "epoch": 0.12536873156342182, "grad_norm": 6.204063892364502, "learning_rate": 2.874631268436578e-05, "loss": 0.7815, "step": 510 }, { "epoch": 0.127826941986234, "grad_norm": 11.101780891418457, "learning_rate": 2.872173058013766e-05, "loss": 0.6533, "step": 520 }, { "epoch": 0.1302851524090462, "grad_norm": 8.723472595214844, "learning_rate": 2.869714847590954e-05, "loss": 0.7021, "step": 530 }, { "epoch": 0.13274336283185842, "grad_norm": 10.951385498046875, "learning_rate": 2.867256637168142e-05, "loss": 0.7019, "step": 540 }, { "epoch": 0.1352015732546706, "grad_norm": 6.301361083984375, "learning_rate": 2.8647984267453293e-05, "loss": 0.624, "step": 550 }, { "epoch": 0.1376597836774828, "grad_norm": 7.326910018920898, "learning_rate": 2.8623402163225173e-05, "loss": 0.714, "step": 560 }, { "epoch": 0.140117994100295, "grad_norm": 12.6168212890625, "learning_rate": 2.859882005899705e-05, "loss": 0.6917, "step": 570 }, { "epoch": 0.14257620452310718, "grad_norm": 10.655887603759766, "learning_rate": 2.857423795476893e-05, "loss": 0.5365, "step": 580 }, { "epoch": 0.14503441494591937, "grad_norm": 14.827045440673828, "learning_rate": 2.8549655850540808e-05, "loss": 0.7906, "step": 590 }, { "epoch": 0.14749262536873156, "grad_norm": 9.008240699768066, "learning_rate": 2.8525073746312685e-05, "loss": 0.5497, "step": 600 }, { "epoch": 0.14995083579154375, "grad_norm": 8.498961448669434, "learning_rate": 2.8500491642084562e-05, "loss": 0.566, "step": 610 }, { "epoch": 0.15240904621435594, "grad_norm": 8.740641593933105, "learning_rate": 2.8475909537856442e-05, "loss": 0.6976, "step": 620 }, { "epoch": 0.15486725663716813, "grad_norm": 9.274945259094238, "learning_rate": 2.845132743362832e-05, "loss": 0.6999, "step": 630 }, { "epoch": 0.15732546705998032, "grad_norm": 6.766937255859375, "learning_rate": 2.84267453294002e-05, "loss": 0.6657, "step": 640 }, { "epoch": 0.1597836774827925, "grad_norm": 16.885639190673828, "learning_rate": 2.8402163225172077e-05, "loss": 0.572, "step": 650 }, { "epoch": 0.16224188790560473, "grad_norm": 8.88036823272705, "learning_rate": 2.8377581120943954e-05, "loss": 0.7973, "step": 660 }, { "epoch": 0.16470009832841692, "grad_norm": 10.527362823486328, "learning_rate": 2.835299901671583e-05, "loss": 0.6466, "step": 670 }, { "epoch": 0.1671583087512291, "grad_norm": 9.253358840942383, "learning_rate": 2.832841691248771e-05, "loss": 0.5154, "step": 680 }, { "epoch": 0.1696165191740413, "grad_norm": 6.103265762329102, "learning_rate": 2.830383480825959e-05, "loss": 0.6569, "step": 690 }, { "epoch": 0.1720747295968535, "grad_norm": 12.258769989013672, "learning_rate": 2.827925270403147e-05, "loss": 0.5404, "step": 700 }, { "epoch": 0.17453294001966568, "grad_norm": 8.478899002075195, "learning_rate": 2.8254670599803343e-05, "loss": 0.6414, "step": 710 }, { "epoch": 0.17699115044247787, "grad_norm": 6.363793849945068, "learning_rate": 2.823008849557522e-05, "loss": 0.4851, "step": 720 }, { "epoch": 0.17944936086529006, "grad_norm": 6.387571811676025, "learning_rate": 2.82055063913471e-05, "loss": 0.6052, "step": 730 }, { "epoch": 0.18190757128810225, "grad_norm": 10.059930801391602, "learning_rate": 2.8180924287118977e-05, "loss": 0.581, "step": 740 }, { "epoch": 0.18436578171091444, "grad_norm": 13.521646499633789, "learning_rate": 2.8156342182890858e-05, "loss": 0.5353, "step": 750 }, { "epoch": 0.18682399213372664, "grad_norm": 12.801778793334961, "learning_rate": 2.813176007866273e-05, "loss": 0.6429, "step": 760 }, { "epoch": 0.18928220255653885, "grad_norm": 4.162469387054443, "learning_rate": 2.8107177974434612e-05, "loss": 0.6899, "step": 770 }, { "epoch": 0.19174041297935104, "grad_norm": 9.74895191192627, "learning_rate": 2.808259587020649e-05, "loss": 0.6106, "step": 780 }, { "epoch": 0.19419862340216323, "grad_norm": 19.779590606689453, "learning_rate": 2.805801376597837e-05, "loss": 0.5259, "step": 790 }, { "epoch": 0.19665683382497542, "grad_norm": 8.597389221191406, "learning_rate": 2.8033431661750246e-05, "loss": 0.6669, "step": 800 }, { "epoch": 0.19911504424778761, "grad_norm": 9.468415260314941, "learning_rate": 2.8008849557522123e-05, "loss": 0.7279, "step": 810 }, { "epoch": 0.2015732546705998, "grad_norm": 7.440244197845459, "learning_rate": 2.7984267453294e-05, "loss": 0.5243, "step": 820 }, { "epoch": 0.204031465093412, "grad_norm": 9.6810941696167, "learning_rate": 2.795968534906588e-05, "loss": 0.4659, "step": 830 }, { "epoch": 0.20648967551622419, "grad_norm": 31.23824119567871, "learning_rate": 2.7935103244837758e-05, "loss": 0.5285, "step": 840 }, { "epoch": 0.20894788593903638, "grad_norm": 7.64473819732666, "learning_rate": 2.7910521140609638e-05, "loss": 0.4728, "step": 850 }, { "epoch": 0.21140609636184857, "grad_norm": 9.734496116638184, "learning_rate": 2.7885939036381515e-05, "loss": 0.642, "step": 860 }, { "epoch": 0.21386430678466076, "grad_norm": 22.392473220825195, "learning_rate": 2.7861356932153392e-05, "loss": 0.6336, "step": 870 }, { "epoch": 0.21632251720747295, "grad_norm": 13.226398468017578, "learning_rate": 2.783677482792527e-05, "loss": 0.5925, "step": 880 }, { "epoch": 0.21878072763028517, "grad_norm": 8.829137802124023, "learning_rate": 2.781219272369715e-05, "loss": 0.6399, "step": 890 }, { "epoch": 0.22123893805309736, "grad_norm": 9.189787864685059, "learning_rate": 2.7787610619469027e-05, "loss": 0.5379, "step": 900 }, { "epoch": 0.22369714847590955, "grad_norm": 8.120711326599121, "learning_rate": 2.7763028515240907e-05, "loss": 0.4276, "step": 910 }, { "epoch": 0.22615535889872174, "grad_norm": 13.711923599243164, "learning_rate": 2.773844641101278e-05, "loss": 0.5053, "step": 920 }, { "epoch": 0.22861356932153393, "grad_norm": 9.840951919555664, "learning_rate": 2.771386430678466e-05, "loss": 0.6218, "step": 930 }, { "epoch": 0.23107177974434612, "grad_norm": 8.518946647644043, "learning_rate": 2.768928220255654e-05, "loss": 0.7532, "step": 940 }, { "epoch": 0.2335299901671583, "grad_norm": 11.203364372253418, "learning_rate": 2.766470009832842e-05, "loss": 0.5558, "step": 950 }, { "epoch": 0.2359882005899705, "grad_norm": 7.044331073760986, "learning_rate": 2.7640117994100296e-05, "loss": 0.5898, "step": 960 }, { "epoch": 0.2384464110127827, "grad_norm": 8.002596855163574, "learning_rate": 2.7615535889872173e-05, "loss": 0.6314, "step": 970 }, { "epoch": 0.24090462143559488, "grad_norm": 5.065498352050781, "learning_rate": 2.759095378564405e-05, "loss": 0.4587, "step": 980 }, { "epoch": 0.24336283185840707, "grad_norm": 8.590278625488281, "learning_rate": 2.756637168141593e-05, "loss": 0.5296, "step": 990 }, { "epoch": 0.24582104228121926, "grad_norm": 9.826451301574707, "learning_rate": 2.7541789577187808e-05, "loss": 0.717, "step": 1000 }, { "epoch": 0.24827925270403148, "grad_norm": 8.760370254516602, "learning_rate": 2.7517207472959688e-05, "loss": 0.5037, "step": 1010 }, { "epoch": 0.25073746312684364, "grad_norm": 12.81543254852295, "learning_rate": 2.7492625368731562e-05, "loss": 0.5835, "step": 1020 }, { "epoch": 0.25319567354965583, "grad_norm": 11.732996940612793, "learning_rate": 2.7468043264503442e-05, "loss": 0.5272, "step": 1030 }, { "epoch": 0.255653883972468, "grad_norm": 8.479822158813477, "learning_rate": 2.744346116027532e-05, "loss": 0.4442, "step": 1040 }, { "epoch": 0.2581120943952802, "grad_norm": 3.572244882583618, "learning_rate": 2.74188790560472e-05, "loss": 0.5766, "step": 1050 }, { "epoch": 0.2605703048180924, "grad_norm": 10.656017303466797, "learning_rate": 2.7394296951819077e-05, "loss": 0.4163, "step": 1060 }, { "epoch": 0.26302851524090465, "grad_norm": 7.770281791687012, "learning_rate": 2.7369714847590954e-05, "loss": 0.4553, "step": 1070 }, { "epoch": 0.26548672566371684, "grad_norm": 9.104904174804688, "learning_rate": 2.734513274336283e-05, "loss": 0.477, "step": 1080 }, { "epoch": 0.26794493608652903, "grad_norm": 10.014952659606934, "learning_rate": 2.732055063913471e-05, "loss": 0.5239, "step": 1090 }, { "epoch": 0.2704031465093412, "grad_norm": 1.713123083114624, "learning_rate": 2.7295968534906588e-05, "loss": 0.5325, "step": 1100 }, { "epoch": 0.2728613569321534, "grad_norm": 5.733578205108643, "learning_rate": 2.727138643067847e-05, "loss": 0.4354, "step": 1110 }, { "epoch": 0.2753195673549656, "grad_norm": 8.82740306854248, "learning_rate": 2.7246804326450346e-05, "loss": 0.4408, "step": 1120 }, { "epoch": 0.2777777777777778, "grad_norm": 8.302656173706055, "learning_rate": 2.7222222222222223e-05, "loss": 0.4801, "step": 1130 }, { "epoch": 0.28023598820059, "grad_norm": 8.672171592712402, "learning_rate": 2.71976401179941e-05, "loss": 0.4674, "step": 1140 }, { "epoch": 0.28269419862340217, "grad_norm": 19.57811164855957, "learning_rate": 2.717305801376598e-05, "loss": 0.7373, "step": 1150 }, { "epoch": 0.28515240904621436, "grad_norm": 5.594559669494629, "learning_rate": 2.7148475909537857e-05, "loss": 0.5339, "step": 1160 }, { "epoch": 0.28761061946902655, "grad_norm": 23.83314323425293, "learning_rate": 2.7123893805309738e-05, "loss": 0.5498, "step": 1170 }, { "epoch": 0.29006882989183874, "grad_norm": 10.187966346740723, "learning_rate": 2.709931170108161e-05, "loss": 0.5103, "step": 1180 }, { "epoch": 0.29252704031465093, "grad_norm": 5.410120487213135, "learning_rate": 2.7074729596853492e-05, "loss": 0.622, "step": 1190 }, { "epoch": 0.2949852507374631, "grad_norm": 5.283186435699463, "learning_rate": 2.705014749262537e-05, "loss": 0.5125, "step": 1200 }, { "epoch": 0.2974434611602753, "grad_norm": 14.078227043151855, "learning_rate": 2.702556538839725e-05, "loss": 0.6187, "step": 1210 }, { "epoch": 0.2999016715830875, "grad_norm": 18.335308074951172, "learning_rate": 2.7000983284169126e-05, "loss": 0.5589, "step": 1220 }, { "epoch": 0.3023598820058997, "grad_norm": 8.976400375366211, "learning_rate": 2.6976401179941004e-05, "loss": 0.5437, "step": 1230 }, { "epoch": 0.3048180924287119, "grad_norm": 5.115795135498047, "learning_rate": 2.695181907571288e-05, "loss": 0.4754, "step": 1240 }, { "epoch": 0.3072763028515241, "grad_norm": 11.577357292175293, "learning_rate": 2.692723697148476e-05, "loss": 0.5659, "step": 1250 }, { "epoch": 0.30973451327433627, "grad_norm": 2.6474692821502686, "learning_rate": 2.6902654867256638e-05, "loss": 0.4822, "step": 1260 }, { "epoch": 0.31219272369714846, "grad_norm": 9.046162605285645, "learning_rate": 2.687807276302852e-05, "loss": 0.4428, "step": 1270 }, { "epoch": 0.31465093411996065, "grad_norm": 6.046942234039307, "learning_rate": 2.6853490658800392e-05, "loss": 0.5371, "step": 1280 }, { "epoch": 0.31710914454277284, "grad_norm": 7.519942283630371, "learning_rate": 2.6828908554572273e-05, "loss": 0.5328, "step": 1290 }, { "epoch": 0.319567354965585, "grad_norm": 9.123747825622559, "learning_rate": 2.680432645034415e-05, "loss": 0.6728, "step": 1300 }, { "epoch": 0.3220255653883973, "grad_norm": 11.151153564453125, "learning_rate": 2.677974434611603e-05, "loss": 0.4258, "step": 1310 }, { "epoch": 0.32448377581120946, "grad_norm": 11.192245483398438, "learning_rate": 2.6755162241887907e-05, "loss": 0.4837, "step": 1320 }, { "epoch": 0.32694198623402165, "grad_norm": 4.427054405212402, "learning_rate": 2.6730580137659784e-05, "loss": 0.5277, "step": 1330 }, { "epoch": 0.32940019665683384, "grad_norm": 5.6805806159973145, "learning_rate": 2.670599803343166e-05, "loss": 0.4547, "step": 1340 }, { "epoch": 0.33185840707964603, "grad_norm": 9.45319652557373, "learning_rate": 2.6681415929203542e-05, "loss": 0.4406, "step": 1350 }, { "epoch": 0.3343166175024582, "grad_norm": 14.050140380859375, "learning_rate": 2.665683382497542e-05, "loss": 0.515, "step": 1360 }, { "epoch": 0.3367748279252704, "grad_norm": 6.314681053161621, "learning_rate": 2.66322517207473e-05, "loss": 0.6452, "step": 1370 }, { "epoch": 0.3392330383480826, "grad_norm": 7.189809799194336, "learning_rate": 2.6607669616519176e-05, "loss": 0.5237, "step": 1380 }, { "epoch": 0.3416912487708948, "grad_norm": 10.517449378967285, "learning_rate": 2.6583087512291053e-05, "loss": 0.5209, "step": 1390 }, { "epoch": 0.344149459193707, "grad_norm": 6.039788722991943, "learning_rate": 2.655850540806293e-05, "loss": 0.3686, "step": 1400 }, { "epoch": 0.3466076696165192, "grad_norm": 10.01025104522705, "learning_rate": 2.653392330383481e-05, "loss": 0.6219, "step": 1410 }, { "epoch": 0.34906588003933137, "grad_norm": 4.097951889038086, "learning_rate": 2.6509341199606688e-05, "loss": 0.4888, "step": 1420 }, { "epoch": 0.35152409046214356, "grad_norm": 11.388020515441895, "learning_rate": 2.6484759095378565e-05, "loss": 0.6765, "step": 1430 }, { "epoch": 0.35398230088495575, "grad_norm": 11.892651557922363, "learning_rate": 2.6460176991150442e-05, "loss": 0.4334, "step": 1440 }, { "epoch": 0.35644051130776794, "grad_norm": 5.7059454917907715, "learning_rate": 2.643559488692232e-05, "loss": 0.3928, "step": 1450 }, { "epoch": 0.35889872173058013, "grad_norm": 10.271086692810059, "learning_rate": 2.64110127826942e-05, "loss": 0.7103, "step": 1460 }, { "epoch": 0.3613569321533923, "grad_norm": 6.829638957977295, "learning_rate": 2.6386430678466077e-05, "loss": 0.425, "step": 1470 }, { "epoch": 0.3638151425762045, "grad_norm": 7.127773284912109, "learning_rate": 2.6361848574237957e-05, "loss": 0.5231, "step": 1480 }, { "epoch": 0.3662733529990167, "grad_norm": 9.82596206665039, "learning_rate": 2.633726647000983e-05, "loss": 0.6525, "step": 1490 }, { "epoch": 0.3687315634218289, "grad_norm": 11.72280216217041, "learning_rate": 2.631268436578171e-05, "loss": 0.5662, "step": 1500 }, { "epoch": 0.3711897738446411, "grad_norm": 5.647986888885498, "learning_rate": 2.6288102261553588e-05, "loss": 0.4917, "step": 1510 }, { "epoch": 0.37364798426745327, "grad_norm": 12.865316390991211, "learning_rate": 2.626352015732547e-05, "loss": 0.5636, "step": 1520 }, { "epoch": 0.37610619469026546, "grad_norm": 35.21678924560547, "learning_rate": 2.6238938053097346e-05, "loss": 0.496, "step": 1530 }, { "epoch": 0.3785644051130777, "grad_norm": 6.413966655731201, "learning_rate": 2.6214355948869223e-05, "loss": 0.4996, "step": 1540 }, { "epoch": 0.3810226155358899, "grad_norm": 10.15141487121582, "learning_rate": 2.61897738446411e-05, "loss": 0.4314, "step": 1550 }, { "epoch": 0.3834808259587021, "grad_norm": 13.585216522216797, "learning_rate": 2.616519174041298e-05, "loss": 0.6773, "step": 1560 }, { "epoch": 0.3859390363815143, "grad_norm": 19.807462692260742, "learning_rate": 2.6140609636184857e-05, "loss": 0.3426, "step": 1570 }, { "epoch": 0.38839724680432647, "grad_norm": 6.755990982055664, "learning_rate": 2.6116027531956738e-05, "loss": 0.4667, "step": 1580 }, { "epoch": 0.39085545722713866, "grad_norm": 5.764073848724365, "learning_rate": 2.609144542772861e-05, "loss": 0.6107, "step": 1590 }, { "epoch": 0.39331366764995085, "grad_norm": 6.236618518829346, "learning_rate": 2.6066863323500492e-05, "loss": 0.5503, "step": 1600 }, { "epoch": 0.39577187807276304, "grad_norm": 5.18848180770874, "learning_rate": 2.604228121927237e-05, "loss": 0.4752, "step": 1610 }, { "epoch": 0.39823008849557523, "grad_norm": 4.610596179962158, "learning_rate": 2.601769911504425e-05, "loss": 0.4523, "step": 1620 }, { "epoch": 0.4006882989183874, "grad_norm": 10.045132637023926, "learning_rate": 2.5993117010816126e-05, "loss": 0.5575, "step": 1630 }, { "epoch": 0.4031465093411996, "grad_norm": 7.4731597900390625, "learning_rate": 2.5968534906588007e-05, "loss": 0.5085, "step": 1640 }, { "epoch": 0.4056047197640118, "grad_norm": 10.281593322753906, "learning_rate": 2.594395280235988e-05, "loss": 0.5317, "step": 1650 }, { "epoch": 0.408062930186824, "grad_norm": 11.010414123535156, "learning_rate": 2.591937069813176e-05, "loss": 0.6036, "step": 1660 }, { "epoch": 0.4105211406096362, "grad_norm": 6.634671688079834, "learning_rate": 2.5894788593903638e-05, "loss": 0.4406, "step": 1670 }, { "epoch": 0.41297935103244837, "grad_norm": 8.043620109558105, "learning_rate": 2.587020648967552e-05, "loss": 0.5872, "step": 1680 }, { "epoch": 0.41543756145526056, "grad_norm": 6.552241325378418, "learning_rate": 2.5845624385447395e-05, "loss": 0.6136, "step": 1690 }, { "epoch": 0.41789577187807275, "grad_norm": 8.951278686523438, "learning_rate": 2.5821042281219272e-05, "loss": 0.4485, "step": 1700 }, { "epoch": 0.42035398230088494, "grad_norm": 8.765510559082031, "learning_rate": 2.579646017699115e-05, "loss": 0.465, "step": 1710 }, { "epoch": 0.42281219272369713, "grad_norm": 7.087189197540283, "learning_rate": 2.577187807276303e-05, "loss": 0.5361, "step": 1720 }, { "epoch": 0.4252704031465093, "grad_norm": 13.196075439453125, "learning_rate": 2.5747295968534907e-05, "loss": 0.5087, "step": 1730 }, { "epoch": 0.4277286135693215, "grad_norm": 7.431585311889648, "learning_rate": 2.5722713864306787e-05, "loss": 0.4733, "step": 1740 }, { "epoch": 0.4301868239921337, "grad_norm": 4.064312934875488, "learning_rate": 2.569813176007866e-05, "loss": 0.4805, "step": 1750 }, { "epoch": 0.4326450344149459, "grad_norm": 6.854459285736084, "learning_rate": 2.567354965585054e-05, "loss": 0.5734, "step": 1760 }, { "epoch": 0.4351032448377581, "grad_norm": 9.38161563873291, "learning_rate": 2.564896755162242e-05, "loss": 0.4498, "step": 1770 }, { "epoch": 0.43756145526057033, "grad_norm": 5.835056304931641, "learning_rate": 2.56243854473943e-05, "loss": 0.4347, "step": 1780 }, { "epoch": 0.4400196656833825, "grad_norm": 9.862078666687012, "learning_rate": 2.5599803343166176e-05, "loss": 0.6373, "step": 1790 }, { "epoch": 0.4424778761061947, "grad_norm": 6.527358531951904, "learning_rate": 2.5575221238938053e-05, "loss": 0.75, "step": 1800 }, { "epoch": 0.4449360865290069, "grad_norm": 11.873770713806152, "learning_rate": 2.555063913470993e-05, "loss": 0.6481, "step": 1810 }, { "epoch": 0.4473942969518191, "grad_norm": 3.437542676925659, "learning_rate": 2.552605703048181e-05, "loss": 0.4321, "step": 1820 }, { "epoch": 0.4498525073746313, "grad_norm": 3.494231939315796, "learning_rate": 2.5501474926253688e-05, "loss": 0.4857, "step": 1830 }, { "epoch": 0.4523107177974435, "grad_norm": 4.382660388946533, "learning_rate": 2.5476892822025568e-05, "loss": 0.5237, "step": 1840 }, { "epoch": 0.45476892822025566, "grad_norm": 2.3829782009124756, "learning_rate": 2.5452310717797445e-05, "loss": 0.4727, "step": 1850 }, { "epoch": 0.45722713864306785, "grad_norm": 9.26497745513916, "learning_rate": 2.5427728613569322e-05, "loss": 0.459, "step": 1860 }, { "epoch": 0.45968534906588004, "grad_norm": 5.994269371032715, "learning_rate": 2.54031465093412e-05, "loss": 0.5014, "step": 1870 }, { "epoch": 0.46214355948869223, "grad_norm": 15.12878704071045, "learning_rate": 2.537856440511308e-05, "loss": 0.5581, "step": 1880 }, { "epoch": 0.4646017699115044, "grad_norm": 5.9776201248168945, "learning_rate": 2.5353982300884957e-05, "loss": 0.5002, "step": 1890 }, { "epoch": 0.4670599803343166, "grad_norm": 9.001272201538086, "learning_rate": 2.5329400196656837e-05, "loss": 0.497, "step": 1900 }, { "epoch": 0.4695181907571288, "grad_norm": 8.775374412536621, "learning_rate": 2.530481809242871e-05, "loss": 0.5575, "step": 1910 }, { "epoch": 0.471976401179941, "grad_norm": 5.382935523986816, "learning_rate": 2.528023598820059e-05, "loss": 0.4937, "step": 1920 }, { "epoch": 0.4744346116027532, "grad_norm": 4.347347259521484, "learning_rate": 2.525565388397247e-05, "loss": 0.4016, "step": 1930 }, { "epoch": 0.4768928220255654, "grad_norm": 5.7770466804504395, "learning_rate": 2.523107177974435e-05, "loss": 0.5552, "step": 1940 }, { "epoch": 0.47935103244837757, "grad_norm": 7.5880937576293945, "learning_rate": 2.5206489675516226e-05, "loss": 0.4567, "step": 1950 }, { "epoch": 0.48180924287118976, "grad_norm": 7.465078353881836, "learning_rate": 2.5181907571288103e-05, "loss": 0.4267, "step": 1960 }, { "epoch": 0.48426745329400195, "grad_norm": 8.554576873779297, "learning_rate": 2.515732546705998e-05, "loss": 0.4802, "step": 1970 }, { "epoch": 0.48672566371681414, "grad_norm": 6.113701820373535, "learning_rate": 2.513274336283186e-05, "loss": 0.4424, "step": 1980 }, { "epoch": 0.48918387413962633, "grad_norm": 9.368378639221191, "learning_rate": 2.5108161258603737e-05, "loss": 0.5942, "step": 1990 }, { "epoch": 0.4916420845624385, "grad_norm": 8.33244800567627, "learning_rate": 2.5083579154375618e-05, "loss": 0.5189, "step": 2000 }, { "epoch": 0.4941002949852507, "grad_norm": 10.917672157287598, "learning_rate": 2.505899705014749e-05, "loss": 0.572, "step": 2010 }, { "epoch": 0.49655850540806296, "grad_norm": 11.998774528503418, "learning_rate": 2.5034414945919372e-05, "loss": 0.5191, "step": 2020 }, { "epoch": 0.49901671583087515, "grad_norm": 6.694921493530273, "learning_rate": 2.500983284169125e-05, "loss": 0.5636, "step": 2030 }, { "epoch": 0.5014749262536873, "grad_norm": 12.438068389892578, "learning_rate": 2.498525073746313e-05, "loss": 0.5056, "step": 2040 }, { "epoch": 0.5039331366764995, "grad_norm": 10.286709785461426, "learning_rate": 2.4960668633235007e-05, "loss": 0.5389, "step": 2050 }, { "epoch": 0.5063913470993117, "grad_norm": 7.132687568664551, "learning_rate": 2.4936086529006884e-05, "loss": 0.5437, "step": 2060 }, { "epoch": 0.5088495575221239, "grad_norm": 6.664190292358398, "learning_rate": 2.491150442477876e-05, "loss": 0.4853, "step": 2070 }, { "epoch": 0.511307767944936, "grad_norm": 9.586512565612793, "learning_rate": 2.488692232055064e-05, "loss": 0.5488, "step": 2080 }, { "epoch": 0.5137659783677483, "grad_norm": 10.750395774841309, "learning_rate": 2.4862340216322518e-05, "loss": 0.5495, "step": 2090 }, { "epoch": 0.5162241887905604, "grad_norm": 7.8294501304626465, "learning_rate": 2.48377581120944e-05, "loss": 0.448, "step": 2100 }, { "epoch": 0.5186823992133727, "grad_norm": 10.0391263961792, "learning_rate": 2.4813176007866276e-05, "loss": 0.4866, "step": 2110 }, { "epoch": 0.5211406096361848, "grad_norm": 3.4506313800811768, "learning_rate": 2.4788593903638153e-05, "loss": 0.3795, "step": 2120 }, { "epoch": 0.523598820058997, "grad_norm": 5.1083807945251465, "learning_rate": 2.476401179941003e-05, "loss": 0.4368, "step": 2130 }, { "epoch": 0.5260570304818093, "grad_norm": 4.659805774688721, "learning_rate": 2.4739429695181907e-05, "loss": 0.6212, "step": 2140 }, { "epoch": 0.5285152409046214, "grad_norm": 3.963684558868408, "learning_rate": 2.4714847590953787e-05, "loss": 0.4124, "step": 2150 }, { "epoch": 0.5309734513274337, "grad_norm": 5.631341934204102, "learning_rate": 2.4690265486725664e-05, "loss": 0.5007, "step": 2160 }, { "epoch": 0.5334316617502458, "grad_norm": 5.105591297149658, "learning_rate": 2.466568338249754e-05, "loss": 0.578, "step": 2170 }, { "epoch": 0.5358898721730581, "grad_norm": 8.802520751953125, "learning_rate": 2.464110127826942e-05, "loss": 0.5633, "step": 2180 }, { "epoch": 0.5383480825958702, "grad_norm": 14.390229225158691, "learning_rate": 2.46165191740413e-05, "loss": 0.5924, "step": 2190 }, { "epoch": 0.5408062930186824, "grad_norm": 11.787581443786621, "learning_rate": 2.4591937069813176e-05, "loss": 0.5352, "step": 2200 }, { "epoch": 0.5432645034414946, "grad_norm": 17.09918975830078, "learning_rate": 2.4567354965585056e-05, "loss": 0.5087, "step": 2210 }, { "epoch": 0.5457227138643068, "grad_norm": 4.868090629577637, "learning_rate": 2.454277286135693e-05, "loss": 0.5794, "step": 2220 }, { "epoch": 0.548180924287119, "grad_norm": 5.864921569824219, "learning_rate": 2.451819075712881e-05, "loss": 0.4658, "step": 2230 }, { "epoch": 0.5506391347099312, "grad_norm": 11.10311508178711, "learning_rate": 2.4493608652900687e-05, "loss": 0.5833, "step": 2240 }, { "epoch": 0.5530973451327433, "grad_norm": 4.954066276550293, "learning_rate": 2.4469026548672568e-05, "loss": 0.4129, "step": 2250 }, { "epoch": 0.5555555555555556, "grad_norm": 12.502214431762695, "learning_rate": 2.4444444444444445e-05, "loss": 0.6587, "step": 2260 }, { "epoch": 0.5580137659783677, "grad_norm": 6.630745887756348, "learning_rate": 2.4419862340216322e-05, "loss": 0.5535, "step": 2270 }, { "epoch": 0.56047197640118, "grad_norm": 15.279702186584473, "learning_rate": 2.43952802359882e-05, "loss": 0.3713, "step": 2280 }, { "epoch": 0.5629301868239921, "grad_norm": 7.2491655349731445, "learning_rate": 2.437069813176008e-05, "loss": 0.5631, "step": 2290 }, { "epoch": 0.5653883972468043, "grad_norm": 9.982495307922363, "learning_rate": 2.4346116027531957e-05, "loss": 0.5518, "step": 2300 }, { "epoch": 0.5678466076696165, "grad_norm": 10.08574104309082, "learning_rate": 2.4321533923303837e-05, "loss": 0.5323, "step": 2310 }, { "epoch": 0.5703048180924287, "grad_norm": 10.688380241394043, "learning_rate": 2.429695181907571e-05, "loss": 0.4256, "step": 2320 }, { "epoch": 0.5727630285152409, "grad_norm": 4.4418487548828125, "learning_rate": 2.427236971484759e-05, "loss": 0.5166, "step": 2330 }, { "epoch": 0.5752212389380531, "grad_norm": 5.143613338470459, "learning_rate": 2.4247787610619468e-05, "loss": 0.5428, "step": 2340 }, { "epoch": 0.5776794493608652, "grad_norm": 13.579387664794922, "learning_rate": 2.422320550639135e-05, "loss": 0.4921, "step": 2350 }, { "epoch": 0.5801376597836775, "grad_norm": 8.991477012634277, "learning_rate": 2.4198623402163226e-05, "loss": 0.4446, "step": 2360 }, { "epoch": 0.5825958702064897, "grad_norm": 5.176370620727539, "learning_rate": 2.4174041297935106e-05, "loss": 0.5818, "step": 2370 }, { "epoch": 0.5850540806293019, "grad_norm": 4.638485908508301, "learning_rate": 2.414945919370698e-05, "loss": 0.4404, "step": 2380 }, { "epoch": 0.5875122910521141, "grad_norm": 12.289114952087402, "learning_rate": 2.412487708947886e-05, "loss": 0.5135, "step": 2390 }, { "epoch": 0.5899705014749262, "grad_norm": 11.608733177185059, "learning_rate": 2.4100294985250737e-05, "loss": 0.4953, "step": 2400 }, { "epoch": 0.5924287118977385, "grad_norm": 14.503495216369629, "learning_rate": 2.4075712881022618e-05, "loss": 0.5782, "step": 2410 }, { "epoch": 0.5948869223205506, "grad_norm": 4.730690956115723, "learning_rate": 2.4051130776794495e-05, "loss": 0.417, "step": 2420 }, { "epoch": 0.5973451327433629, "grad_norm": 15.554600715637207, "learning_rate": 2.4026548672566372e-05, "loss": 0.4633, "step": 2430 }, { "epoch": 0.599803343166175, "grad_norm": 8.06122875213623, "learning_rate": 2.400196656833825e-05, "loss": 0.5808, "step": 2440 }, { "epoch": 0.6022615535889873, "grad_norm": 5.744154453277588, "learning_rate": 2.397738446411013e-05, "loss": 0.5237, "step": 2450 }, { "epoch": 0.6047197640117994, "grad_norm": 8.59859561920166, "learning_rate": 2.3952802359882006e-05, "loss": 0.5775, "step": 2460 }, { "epoch": 0.6071779744346116, "grad_norm": 9.3620023727417, "learning_rate": 2.3928220255653887e-05, "loss": 0.5577, "step": 2470 }, { "epoch": 0.6096361848574238, "grad_norm": 8.121408462524414, "learning_rate": 2.390363815142576e-05, "loss": 0.4174, "step": 2480 }, { "epoch": 0.612094395280236, "grad_norm": 4.134389877319336, "learning_rate": 2.387905604719764e-05, "loss": 0.3753, "step": 2490 }, { "epoch": 0.6145526057030481, "grad_norm": 6.272571563720703, "learning_rate": 2.3854473942969518e-05, "loss": 0.4387, "step": 2500 }, { "epoch": 0.6170108161258604, "grad_norm": 18.297719955444336, "learning_rate": 2.38298918387414e-05, "loss": 0.5838, "step": 2510 }, { "epoch": 0.6194690265486725, "grad_norm": 12.328811645507812, "learning_rate": 2.3805309734513275e-05, "loss": 0.533, "step": 2520 }, { "epoch": 0.6219272369714848, "grad_norm": 3.174924850463867, "learning_rate": 2.3780727630285152e-05, "loss": 0.6027, "step": 2530 }, { "epoch": 0.6243854473942969, "grad_norm": 5.742171764373779, "learning_rate": 2.375614552605703e-05, "loss": 0.5088, "step": 2540 }, { "epoch": 0.6268436578171092, "grad_norm": 3.0802981853485107, "learning_rate": 2.373156342182891e-05, "loss": 0.5705, "step": 2550 }, { "epoch": 0.6293018682399213, "grad_norm": 6.47110652923584, "learning_rate": 2.3706981317600787e-05, "loss": 0.5281, "step": 2560 }, { "epoch": 0.6317600786627335, "grad_norm": 8.59976863861084, "learning_rate": 2.3682399213372667e-05, "loss": 0.4775, "step": 2570 }, { "epoch": 0.6342182890855457, "grad_norm": 3.876051902770996, "learning_rate": 2.365781710914454e-05, "loss": 0.5044, "step": 2580 }, { "epoch": 0.6366764995083579, "grad_norm": 4.963217258453369, "learning_rate": 2.363323500491642e-05, "loss": 0.3695, "step": 2590 }, { "epoch": 0.63913470993117, "grad_norm": 6.193314075469971, "learning_rate": 2.36086529006883e-05, "loss": 0.3693, "step": 2600 }, { "epoch": 0.6415929203539823, "grad_norm": 8.763198852539062, "learning_rate": 2.358407079646018e-05, "loss": 0.5671, "step": 2610 }, { "epoch": 0.6440511307767945, "grad_norm": 14.428309440612793, "learning_rate": 2.3559488692232056e-05, "loss": 0.4745, "step": 2620 }, { "epoch": 0.6465093411996067, "grad_norm": 6.042642593383789, "learning_rate": 2.3534906588003937e-05, "loss": 0.5435, "step": 2630 }, { "epoch": 0.6489675516224189, "grad_norm": 5.525725364685059, "learning_rate": 2.351032448377581e-05, "loss": 0.5447, "step": 2640 }, { "epoch": 0.6514257620452311, "grad_norm": 8.800530433654785, "learning_rate": 2.348574237954769e-05, "loss": 0.5015, "step": 2650 }, { "epoch": 0.6538839724680433, "grad_norm": 10.362552642822266, "learning_rate": 2.3461160275319568e-05, "loss": 0.5359, "step": 2660 }, { "epoch": 0.6563421828908554, "grad_norm": 6.188908100128174, "learning_rate": 2.3436578171091448e-05, "loss": 0.4262, "step": 2670 }, { "epoch": 0.6588003933136677, "grad_norm": 10.73771858215332, "learning_rate": 2.3411996066863325e-05, "loss": 0.482, "step": 2680 }, { "epoch": 0.6612586037364798, "grad_norm": 7.361353874206543, "learning_rate": 2.3387413962635202e-05, "loss": 0.5991, "step": 2690 }, { "epoch": 0.6637168141592921, "grad_norm": 7.3403096199035645, "learning_rate": 2.336283185840708e-05, "loss": 0.333, "step": 2700 }, { "epoch": 0.6661750245821042, "grad_norm": 7.783878326416016, "learning_rate": 2.333824975417896e-05, "loss": 0.5146, "step": 2710 }, { "epoch": 0.6686332350049164, "grad_norm": 9.952214241027832, "learning_rate": 2.3313667649950837e-05, "loss": 0.5144, "step": 2720 }, { "epoch": 0.6710914454277286, "grad_norm": 4.199956893920898, "learning_rate": 2.3289085545722717e-05, "loss": 0.4372, "step": 2730 }, { "epoch": 0.6735496558505408, "grad_norm": 11.640962600708008, "learning_rate": 2.326450344149459e-05, "loss": 0.4177, "step": 2740 }, { "epoch": 0.676007866273353, "grad_norm": 5.427495956420898, "learning_rate": 2.323992133726647e-05, "loss": 0.4815, "step": 2750 }, { "epoch": 0.6784660766961652, "grad_norm": 10.226431846618652, "learning_rate": 2.321533923303835e-05, "loss": 0.5361, "step": 2760 }, { "epoch": 0.6809242871189773, "grad_norm": 11.579864501953125, "learning_rate": 2.319075712881023e-05, "loss": 0.5135, "step": 2770 }, { "epoch": 0.6833824975417896, "grad_norm": 3.3046741485595703, "learning_rate": 2.3166175024582106e-05, "loss": 0.4778, "step": 2780 }, { "epoch": 0.6858407079646017, "grad_norm": 9.913078308105469, "learning_rate": 2.3141592920353983e-05, "loss": 0.3821, "step": 2790 }, { "epoch": 0.688298918387414, "grad_norm": 9.077658653259277, "learning_rate": 2.311701081612586e-05, "loss": 0.6499, "step": 2800 }, { "epoch": 0.6907571288102261, "grad_norm": 3.8389570713043213, "learning_rate": 2.309242871189774e-05, "loss": 0.4617, "step": 2810 }, { "epoch": 0.6932153392330384, "grad_norm": 9.970629692077637, "learning_rate": 2.3067846607669617e-05, "loss": 0.4458, "step": 2820 }, { "epoch": 0.6956735496558505, "grad_norm": 8.259069442749023, "learning_rate": 2.3043264503441498e-05, "loss": 0.4975, "step": 2830 }, { "epoch": 0.6981317600786627, "grad_norm": 6.121667385101318, "learning_rate": 2.301868239921337e-05, "loss": 0.495, "step": 2840 }, { "epoch": 0.700589970501475, "grad_norm": 7.604616165161133, "learning_rate": 2.299410029498525e-05, "loss": 0.6211, "step": 2850 }, { "epoch": 0.7030481809242871, "grad_norm": 17.521102905273438, "learning_rate": 2.296951819075713e-05, "loss": 0.4487, "step": 2860 }, { "epoch": 0.7055063913470994, "grad_norm": 4.555481433868408, "learning_rate": 2.2944936086529006e-05, "loss": 0.4879, "step": 2870 }, { "epoch": 0.7079646017699115, "grad_norm": 4.537175178527832, "learning_rate": 2.2920353982300887e-05, "loss": 0.6027, "step": 2880 }, { "epoch": 0.7104228121927237, "grad_norm": 7.973269462585449, "learning_rate": 2.2895771878072764e-05, "loss": 0.5717, "step": 2890 }, { "epoch": 0.7128810226155359, "grad_norm": 5.742907524108887, "learning_rate": 2.287118977384464e-05, "loss": 0.3806, "step": 2900 }, { "epoch": 0.7153392330383481, "grad_norm": 14.055597305297852, "learning_rate": 2.2846607669616518e-05, "loss": 0.4483, "step": 2910 }, { "epoch": 0.7177974434611603, "grad_norm": 7.573107719421387, "learning_rate": 2.2822025565388398e-05, "loss": 0.3967, "step": 2920 }, { "epoch": 0.7202556538839725, "grad_norm": 13.468011856079102, "learning_rate": 2.2797443461160275e-05, "loss": 0.4698, "step": 2930 }, { "epoch": 0.7227138643067846, "grad_norm": 16.700359344482422, "learning_rate": 2.2772861356932156e-05, "loss": 0.454, "step": 2940 }, { "epoch": 0.7251720747295969, "grad_norm": 5.207769393920898, "learning_rate": 2.274827925270403e-05, "loss": 0.4568, "step": 2950 }, { "epoch": 0.727630285152409, "grad_norm": 17.724849700927734, "learning_rate": 2.272369714847591e-05, "loss": 0.3999, "step": 2960 }, { "epoch": 0.7300884955752213, "grad_norm": 7.871232032775879, "learning_rate": 2.2699115044247787e-05, "loss": 0.5303, "step": 2970 }, { "epoch": 0.7325467059980334, "grad_norm": 9.913866996765137, "learning_rate": 2.2674532940019667e-05, "loss": 0.5922, "step": 2980 }, { "epoch": 0.7350049164208456, "grad_norm": 6.655422687530518, "learning_rate": 2.2649950835791544e-05, "loss": 0.4875, "step": 2990 }, { "epoch": 0.7374631268436578, "grad_norm": 12.307462692260742, "learning_rate": 2.262536873156342e-05, "loss": 0.5307, "step": 3000 }, { "epoch": 0.73992133726647, "grad_norm": 5.370288372039795, "learning_rate": 2.26007866273353e-05, "loss": 0.5166, "step": 3010 }, { "epoch": 0.7423795476892822, "grad_norm": 4.290733337402344, "learning_rate": 2.257620452310718e-05, "loss": 0.5331, "step": 3020 }, { "epoch": 0.7448377581120944, "grad_norm": 5.392223834991455, "learning_rate": 2.2551622418879056e-05, "loss": 0.4304, "step": 3030 }, { "epoch": 0.7472959685349065, "grad_norm": 12.91469955444336, "learning_rate": 2.2527040314650936e-05, "loss": 0.5358, "step": 3040 }, { "epoch": 0.7497541789577188, "grad_norm": 5.212155818939209, "learning_rate": 2.250245821042281e-05, "loss": 0.5354, "step": 3050 }, { "epoch": 0.7522123893805309, "grad_norm": 5.4907121658325195, "learning_rate": 2.247787610619469e-05, "loss": 0.5198, "step": 3060 }, { "epoch": 0.7546705998033432, "grad_norm": 8.176883697509766, "learning_rate": 2.2453294001966567e-05, "loss": 0.5189, "step": 3070 }, { "epoch": 0.7571288102261554, "grad_norm": 12.968071937561035, "learning_rate": 2.2428711897738448e-05, "loss": 0.4357, "step": 3080 }, { "epoch": 0.7595870206489675, "grad_norm": 11.673113822937012, "learning_rate": 2.2404129793510325e-05, "loss": 0.5656, "step": 3090 }, { "epoch": 0.7620452310717798, "grad_norm": 4.480779647827148, "learning_rate": 2.2379547689282205e-05, "loss": 0.5133, "step": 3100 }, { "epoch": 0.7645034414945919, "grad_norm": 19.073516845703125, "learning_rate": 2.235496558505408e-05, "loss": 0.3882, "step": 3110 }, { "epoch": 0.7669616519174042, "grad_norm": 22.255006790161133, "learning_rate": 2.233038348082596e-05, "loss": 0.4554, "step": 3120 }, { "epoch": 0.7694198623402163, "grad_norm": 9.34777545928955, "learning_rate": 2.2305801376597837e-05, "loss": 0.526, "step": 3130 }, { "epoch": 0.7718780727630286, "grad_norm": 13.343056678771973, "learning_rate": 2.2281219272369717e-05, "loss": 0.4428, "step": 3140 }, { "epoch": 0.7743362831858407, "grad_norm": 5.4399638175964355, "learning_rate": 2.2256637168141594e-05, "loss": 0.4282, "step": 3150 }, { "epoch": 0.7767944936086529, "grad_norm": 8.172656059265137, "learning_rate": 2.223205506391347e-05, "loss": 0.4102, "step": 3160 }, { "epoch": 0.7792527040314651, "grad_norm": 8.033787727355957, "learning_rate": 2.2207472959685348e-05, "loss": 0.4884, "step": 3170 }, { "epoch": 0.7817109144542773, "grad_norm": 4.783967971801758, "learning_rate": 2.218289085545723e-05, "loss": 0.541, "step": 3180 }, { "epoch": 0.7841691248770895, "grad_norm": 6.006264686584473, "learning_rate": 2.2158308751229106e-05, "loss": 0.5675, "step": 3190 }, { "epoch": 0.7866273352999017, "grad_norm": 7.555843830108643, "learning_rate": 2.2133726647000986e-05, "loss": 0.5561, "step": 3200 }, { "epoch": 0.7890855457227138, "grad_norm": 8.102278709411621, "learning_rate": 2.210914454277286e-05, "loss": 0.5674, "step": 3210 }, { "epoch": 0.7915437561455261, "grad_norm": 3.9618332386016846, "learning_rate": 2.208456243854474e-05, "loss": 0.4651, "step": 3220 }, { "epoch": 0.7940019665683382, "grad_norm": 6.619464874267578, "learning_rate": 2.2059980334316617e-05, "loss": 0.4607, "step": 3230 }, { "epoch": 0.7964601769911505, "grad_norm": 6.925910472869873, "learning_rate": 2.2035398230088498e-05, "loss": 0.4836, "step": 3240 }, { "epoch": 0.7989183874139626, "grad_norm": 9.410330772399902, "learning_rate": 2.2010816125860375e-05, "loss": 0.579, "step": 3250 }, { "epoch": 0.8013765978367748, "grad_norm": 3.5774123668670654, "learning_rate": 2.1986234021632252e-05, "loss": 0.4461, "step": 3260 }, { "epoch": 0.803834808259587, "grad_norm": 5.161646366119385, "learning_rate": 2.196165191740413e-05, "loss": 0.4428, "step": 3270 }, { "epoch": 0.8062930186823992, "grad_norm": 5.34110164642334, "learning_rate": 2.193706981317601e-05, "loss": 0.4502, "step": 3280 }, { "epoch": 0.8087512291052114, "grad_norm": 4.516976833343506, "learning_rate": 2.1912487708947886e-05, "loss": 0.4309, "step": 3290 }, { "epoch": 0.8112094395280236, "grad_norm": 9.512310981750488, "learning_rate": 2.1887905604719767e-05, "loss": 0.3653, "step": 3300 }, { "epoch": 0.8136676499508357, "grad_norm": 6.483795642852783, "learning_rate": 2.186332350049164e-05, "loss": 0.5198, "step": 3310 }, { "epoch": 0.816125860373648, "grad_norm": 8.581228256225586, "learning_rate": 2.183874139626352e-05, "loss": 0.5199, "step": 3320 }, { "epoch": 0.8185840707964602, "grad_norm": 4.572148323059082, "learning_rate": 2.1814159292035398e-05, "loss": 0.4326, "step": 3330 }, { "epoch": 0.8210422812192724, "grad_norm": 6.907229423522949, "learning_rate": 2.178957718780728e-05, "loss": 0.4335, "step": 3340 }, { "epoch": 0.8235004916420846, "grad_norm": 7.584132671356201, "learning_rate": 2.1764995083579155e-05, "loss": 0.5398, "step": 3350 }, { "epoch": 0.8259587020648967, "grad_norm": 13.972970008850098, "learning_rate": 2.1740412979351036e-05, "loss": 0.4103, "step": 3360 }, { "epoch": 0.828416912487709, "grad_norm": 8.90891170501709, "learning_rate": 2.171583087512291e-05, "loss": 0.466, "step": 3370 }, { "epoch": 0.8308751229105211, "grad_norm": 2.0755972862243652, "learning_rate": 2.169124877089479e-05, "loss": 0.593, "step": 3380 }, { "epoch": 0.8333333333333334, "grad_norm": 14.203392028808594, "learning_rate": 2.1666666666666667e-05, "loss": 0.4755, "step": 3390 }, { "epoch": 0.8357915437561455, "grad_norm": 8.946110725402832, "learning_rate": 2.1642084562438547e-05, "loss": 0.419, "step": 3400 }, { "epoch": 0.8382497541789578, "grad_norm": 6.248900413513184, "learning_rate": 2.1617502458210425e-05, "loss": 0.4872, "step": 3410 }, { "epoch": 0.8407079646017699, "grad_norm": 2.8045787811279297, "learning_rate": 2.15929203539823e-05, "loss": 0.3869, "step": 3420 }, { "epoch": 0.8431661750245821, "grad_norm": 14.361637115478516, "learning_rate": 2.156833824975418e-05, "loss": 0.4241, "step": 3430 }, { "epoch": 0.8456243854473943, "grad_norm": 15.096592903137207, "learning_rate": 2.154375614552606e-05, "loss": 0.478, "step": 3440 }, { "epoch": 0.8480825958702065, "grad_norm": 7.954670429229736, "learning_rate": 2.1519174041297936e-05, "loss": 0.4304, "step": 3450 }, { "epoch": 0.8505408062930186, "grad_norm": 4.873976230621338, "learning_rate": 2.1494591937069817e-05, "loss": 0.5241, "step": 3460 }, { "epoch": 0.8529990167158309, "grad_norm": 11.766910552978516, "learning_rate": 2.147000983284169e-05, "loss": 0.5613, "step": 3470 }, { "epoch": 0.855457227138643, "grad_norm": 3.6245765686035156, "learning_rate": 2.144542772861357e-05, "loss": 0.5307, "step": 3480 }, { "epoch": 0.8579154375614553, "grad_norm": 15.422343254089355, "learning_rate": 2.1420845624385448e-05, "loss": 0.499, "step": 3490 }, { "epoch": 0.8603736479842674, "grad_norm": 7.901346683502197, "learning_rate": 2.1396263520157328e-05, "loss": 0.5322, "step": 3500 }, { "epoch": 0.8628318584070797, "grad_norm": 18.303707122802734, "learning_rate": 2.1371681415929205e-05, "loss": 0.4812, "step": 3510 }, { "epoch": 0.8652900688298918, "grad_norm": 12.986900329589844, "learning_rate": 2.1347099311701082e-05, "loss": 0.4591, "step": 3520 }, { "epoch": 0.867748279252704, "grad_norm": 3.7609236240386963, "learning_rate": 2.132251720747296e-05, "loss": 0.4742, "step": 3530 }, { "epoch": 0.8702064896755162, "grad_norm": 3.7630157470703125, "learning_rate": 2.129793510324484e-05, "loss": 0.4966, "step": 3540 }, { "epoch": 0.8726647000983284, "grad_norm": 16.763559341430664, "learning_rate": 2.1273352999016717e-05, "loss": 0.6154, "step": 3550 }, { "epoch": 0.8751229105211407, "grad_norm": 8.081168174743652, "learning_rate": 2.1248770894788594e-05, "loss": 0.4589, "step": 3560 }, { "epoch": 0.8775811209439528, "grad_norm": 6.508256435394287, "learning_rate": 2.122418879056047e-05, "loss": 0.5077, "step": 3570 }, { "epoch": 0.880039331366765, "grad_norm": 7.4091105461120605, "learning_rate": 2.1199606686332348e-05, "loss": 0.5019, "step": 3580 }, { "epoch": 0.8824975417895772, "grad_norm": 4.946775436401367, "learning_rate": 2.117502458210423e-05, "loss": 0.4029, "step": 3590 }, { "epoch": 0.8849557522123894, "grad_norm": 6.103461742401123, "learning_rate": 2.1150442477876105e-05, "loss": 0.4649, "step": 3600 }, { "epoch": 0.8874139626352016, "grad_norm": 6.599686622619629, "learning_rate": 2.1125860373647986e-05, "loss": 0.3877, "step": 3610 }, { "epoch": 0.8898721730580138, "grad_norm": 5.916107177734375, "learning_rate": 2.1101278269419863e-05, "loss": 0.5621, "step": 3620 }, { "epoch": 0.8923303834808259, "grad_norm": 8.876946449279785, "learning_rate": 2.107669616519174e-05, "loss": 0.5249, "step": 3630 }, { "epoch": 0.8947885939036382, "grad_norm": 2.116217851638794, "learning_rate": 2.1052114060963617e-05, "loss": 0.3876, "step": 3640 }, { "epoch": 0.8972468043264503, "grad_norm": 15.19304370880127, "learning_rate": 2.1027531956735497e-05, "loss": 0.5802, "step": 3650 }, { "epoch": 0.8997050147492626, "grad_norm": 11.525105476379395, "learning_rate": 2.1002949852507375e-05, "loss": 0.4713, "step": 3660 }, { "epoch": 0.9021632251720747, "grad_norm": 13.997809410095215, "learning_rate": 2.0978367748279255e-05, "loss": 0.5222, "step": 3670 }, { "epoch": 0.904621435594887, "grad_norm": 20.39089012145996, "learning_rate": 2.095378564405113e-05, "loss": 0.4762, "step": 3680 }, { "epoch": 0.9070796460176991, "grad_norm": 10.223085403442383, "learning_rate": 2.092920353982301e-05, "loss": 0.4369, "step": 3690 }, { "epoch": 0.9095378564405113, "grad_norm": 7.517868518829346, "learning_rate": 2.0904621435594886e-05, "loss": 0.4634, "step": 3700 }, { "epoch": 0.9119960668633235, "grad_norm": 3.218001127243042, "learning_rate": 2.0880039331366767e-05, "loss": 0.3456, "step": 3710 }, { "epoch": 0.9144542772861357, "grad_norm": 9.376920700073242, "learning_rate": 2.0855457227138644e-05, "loss": 0.5695, "step": 3720 }, { "epoch": 0.9169124877089478, "grad_norm": 3.81313157081604, "learning_rate": 2.083087512291052e-05, "loss": 0.4456, "step": 3730 }, { "epoch": 0.9193706981317601, "grad_norm": 8.369253158569336, "learning_rate": 2.0806293018682398e-05, "loss": 0.4699, "step": 3740 }, { "epoch": 0.9218289085545722, "grad_norm": 14.757840156555176, "learning_rate": 2.0781710914454278e-05, "loss": 0.4203, "step": 3750 }, { "epoch": 0.9242871189773845, "grad_norm": 6.23776388168335, "learning_rate": 2.0757128810226155e-05, "loss": 0.5059, "step": 3760 }, { "epoch": 0.9267453294001966, "grad_norm": 3.1502370834350586, "learning_rate": 2.0732546705998036e-05, "loss": 0.5431, "step": 3770 }, { "epoch": 0.9292035398230089, "grad_norm": 7.7508673667907715, "learning_rate": 2.070796460176991e-05, "loss": 0.5423, "step": 3780 }, { "epoch": 0.9316617502458211, "grad_norm": 13.38754653930664, "learning_rate": 2.068338249754179e-05, "loss": 0.3934, "step": 3790 }, { "epoch": 0.9341199606686332, "grad_norm": 7.397925853729248, "learning_rate": 2.0658800393313667e-05, "loss": 0.4518, "step": 3800 }, { "epoch": 0.9365781710914455, "grad_norm": 6.277956485748291, "learning_rate": 2.0634218289085547e-05, "loss": 0.5124, "step": 3810 }, { "epoch": 0.9390363815142576, "grad_norm": 6.064617156982422, "learning_rate": 2.0609636184857424e-05, "loss": 0.5533, "step": 3820 }, { "epoch": 0.9414945919370699, "grad_norm": 14.695613861083984, "learning_rate": 2.05850540806293e-05, "loss": 0.4194, "step": 3830 }, { "epoch": 0.943952802359882, "grad_norm": 7.271769046783447, "learning_rate": 2.056047197640118e-05, "loss": 0.4003, "step": 3840 }, { "epoch": 0.9464110127826942, "grad_norm": 5.177496910095215, "learning_rate": 2.053588987217306e-05, "loss": 0.4745, "step": 3850 }, { "epoch": 0.9488692232055064, "grad_norm": 8.757434844970703, "learning_rate": 2.0511307767944936e-05, "loss": 0.592, "step": 3860 }, { "epoch": 0.9513274336283186, "grad_norm": 25.987625122070312, "learning_rate": 2.0486725663716816e-05, "loss": 0.4387, "step": 3870 }, { "epoch": 0.9537856440511308, "grad_norm": 10.042795181274414, "learning_rate": 2.0462143559488693e-05, "loss": 0.6556, "step": 3880 }, { "epoch": 0.956243854473943, "grad_norm": 6.292783737182617, "learning_rate": 2.043756145526057e-05, "loss": 0.5829, "step": 3890 }, { "epoch": 0.9587020648967551, "grad_norm": 17.702865600585938, "learning_rate": 2.0412979351032448e-05, "loss": 0.5239, "step": 3900 }, { "epoch": 0.9611602753195674, "grad_norm": 12.397199630737305, "learning_rate": 2.0388397246804328e-05, "loss": 0.4999, "step": 3910 }, { "epoch": 0.9636184857423795, "grad_norm": 6.144417762756348, "learning_rate": 2.0363815142576205e-05, "loss": 0.4409, "step": 3920 }, { "epoch": 0.9660766961651918, "grad_norm": 8.322697639465332, "learning_rate": 2.0339233038348085e-05, "loss": 0.4495, "step": 3930 }, { "epoch": 0.9685349065880039, "grad_norm": 6.333006381988525, "learning_rate": 2.031465093411996e-05, "loss": 0.4277, "step": 3940 }, { "epoch": 0.9709931170108161, "grad_norm": 8.983305931091309, "learning_rate": 2.029006882989184e-05, "loss": 0.5601, "step": 3950 }, { "epoch": 0.9734513274336283, "grad_norm": 5.597654342651367, "learning_rate": 2.0265486725663717e-05, "loss": 0.3, "step": 3960 }, { "epoch": 0.9759095378564405, "grad_norm": 14.860602378845215, "learning_rate": 2.0240904621435597e-05, "loss": 0.4716, "step": 3970 }, { "epoch": 0.9783677482792527, "grad_norm": 10.39282512664795, "learning_rate": 2.0216322517207474e-05, "loss": 0.491, "step": 3980 }, { "epoch": 0.9808259587020649, "grad_norm": 5.0894036293029785, "learning_rate": 2.019174041297935e-05, "loss": 0.4139, "step": 3990 }, { "epoch": 0.983284169124877, "grad_norm": 13.351344108581543, "learning_rate": 2.0167158308751228e-05, "loss": 0.3799, "step": 4000 }, { "epoch": 0.9857423795476893, "grad_norm": 5.922131538391113, "learning_rate": 2.014257620452311e-05, "loss": 0.4492, "step": 4010 }, { "epoch": 0.9882005899705014, "grad_norm": 1.4785284996032715, "learning_rate": 2.0117994100294986e-05, "loss": 0.4584, "step": 4020 }, { "epoch": 0.9906588003933137, "grad_norm": 2.5540578365325928, "learning_rate": 2.0093411996066866e-05, "loss": 0.4836, "step": 4030 }, { "epoch": 0.9931170108161259, "grad_norm": 7.5396857261657715, "learning_rate": 2.006882989183874e-05, "loss": 0.5474, "step": 4040 }, { "epoch": 0.995575221238938, "grad_norm": 9.396368980407715, "learning_rate": 2.004424778761062e-05, "loss": 0.5548, "step": 4050 }, { "epoch": 0.9980334316617503, "grad_norm": 25.47150993347168, "learning_rate": 2.0019665683382497e-05, "loss": 0.5946, "step": 4060 }, { "epoch": 1.0, "eval_accuracy": 0.8398561748029318, "eval_f1_score": 0.8350345608848432, "eval_loss": 0.4522732198238373, "eval_runtime": 115.6206, "eval_samples_per_second": 62.541, "eval_steps_per_second": 3.909, "step": 4068 }, { "epoch": 1.0004916420845624, "grad_norm": 3.885512590408325, "learning_rate": 1.9995083579154378e-05, "loss": 0.4428, "step": 4070 }, { "epoch": 1.0029498525073746, "grad_norm": 10.224822044372559, "learning_rate": 1.9970501474926255e-05, "loss": 0.5206, "step": 4080 }, { "epoch": 1.005408062930187, "grad_norm": 7.797532558441162, "learning_rate": 1.9945919370698135e-05, "loss": 0.4241, "step": 4090 }, { "epoch": 1.007866273352999, "grad_norm": 9.218301773071289, "learning_rate": 1.992133726647001e-05, "loss": 0.4255, "step": 4100 }, { "epoch": 1.0103244837758112, "grad_norm": 10.955337524414062, "learning_rate": 1.989675516224189e-05, "loss": 0.4345, "step": 4110 }, { "epoch": 1.0127826941986233, "grad_norm": 14.320428848266602, "learning_rate": 1.9872173058013766e-05, "loss": 0.3475, "step": 4120 }, { "epoch": 1.0152409046214357, "grad_norm": 8.566821098327637, "learning_rate": 1.9847590953785647e-05, "loss": 0.3889, "step": 4130 }, { "epoch": 1.0176991150442478, "grad_norm": 11.800101280212402, "learning_rate": 1.9823008849557524e-05, "loss": 0.3114, "step": 4140 }, { "epoch": 1.02015732546706, "grad_norm": 11.478809356689453, "learning_rate": 1.97984267453294e-05, "loss": 0.4566, "step": 4150 }, { "epoch": 1.022615535889872, "grad_norm": 4.499897480010986, "learning_rate": 1.9773844641101278e-05, "loss": 0.411, "step": 4160 }, { "epoch": 1.0250737463126844, "grad_norm": 11.2285737991333, "learning_rate": 1.974926253687316e-05, "loss": 0.365, "step": 4170 }, { "epoch": 1.0275319567354966, "grad_norm": 10.22508430480957, "learning_rate": 1.9724680432645035e-05, "loss": 0.4283, "step": 4180 }, { "epoch": 1.0299901671583087, "grad_norm": 4.208901882171631, "learning_rate": 1.9700098328416916e-05, "loss": 0.3784, "step": 4190 }, { "epoch": 1.0324483775811208, "grad_norm": 6.89427375793457, "learning_rate": 1.967551622418879e-05, "loss": 0.2619, "step": 4200 }, { "epoch": 1.0349065880039332, "grad_norm": 7.281291484832764, "learning_rate": 1.965093411996067e-05, "loss": 0.5831, "step": 4210 }, { "epoch": 1.0373647984267453, "grad_norm": 8.588820457458496, "learning_rate": 1.9626352015732547e-05, "loss": 0.3714, "step": 4220 }, { "epoch": 1.0398230088495575, "grad_norm": 15.088011741638184, "learning_rate": 1.9601769911504427e-05, "loss": 0.4533, "step": 4230 }, { "epoch": 1.0422812192723696, "grad_norm": 7.60711669921875, "learning_rate": 1.9577187807276305e-05, "loss": 0.3713, "step": 4240 }, { "epoch": 1.044739429695182, "grad_norm": 2.3092093467712402, "learning_rate": 1.955260570304818e-05, "loss": 0.3328, "step": 4250 }, { "epoch": 1.047197640117994, "grad_norm": 6.415675640106201, "learning_rate": 1.952802359882006e-05, "loss": 0.4717, "step": 4260 }, { "epoch": 1.0496558505408062, "grad_norm": 3.487186908721924, "learning_rate": 1.9503441494591936e-05, "loss": 0.3299, "step": 4270 }, { "epoch": 1.0521140609636186, "grad_norm": 7.219429016113281, "learning_rate": 1.9478859390363816e-05, "loss": 0.3611, "step": 4280 }, { "epoch": 1.0545722713864307, "grad_norm": 8.66403579711914, "learning_rate": 1.9454277286135693e-05, "loss": 0.3974, "step": 4290 }, { "epoch": 1.0570304818092429, "grad_norm": 11.184769630432129, "learning_rate": 1.942969518190757e-05, "loss": 0.3343, "step": 4300 }, { "epoch": 1.059488692232055, "grad_norm": 13.870694160461426, "learning_rate": 1.9405113077679447e-05, "loss": 0.4417, "step": 4310 }, { "epoch": 1.0619469026548674, "grad_norm": 23.112136840820312, "learning_rate": 1.9380530973451328e-05, "loss": 0.5344, "step": 4320 }, { "epoch": 1.0644051130776795, "grad_norm": 9.18332576751709, "learning_rate": 1.9355948869223205e-05, "loss": 0.4197, "step": 4330 }, { "epoch": 1.0668633235004916, "grad_norm": 5.6918439865112305, "learning_rate": 1.9331366764995085e-05, "loss": 0.3515, "step": 4340 }, { "epoch": 1.0693215339233038, "grad_norm": 8.93621826171875, "learning_rate": 1.9306784660766962e-05, "loss": 0.4377, "step": 4350 }, { "epoch": 1.0717797443461161, "grad_norm": 7.420980453491211, "learning_rate": 1.928220255653884e-05, "loss": 0.3559, "step": 4360 }, { "epoch": 1.0742379547689282, "grad_norm": 12.044346809387207, "learning_rate": 1.9257620452310716e-05, "loss": 0.3253, "step": 4370 }, { "epoch": 1.0766961651917404, "grad_norm": 9.863391876220703, "learning_rate": 1.9233038348082597e-05, "loss": 0.4338, "step": 4380 }, { "epoch": 1.0791543756145525, "grad_norm": 4.251192092895508, "learning_rate": 1.9208456243854474e-05, "loss": 0.4389, "step": 4390 }, { "epoch": 1.0816125860373649, "grad_norm": 10.624669075012207, "learning_rate": 1.9183874139626354e-05, "loss": 0.404, "step": 4400 }, { "epoch": 1.084070796460177, "grad_norm": 12.453062057495117, "learning_rate": 1.9159292035398228e-05, "loss": 0.4288, "step": 4410 }, { "epoch": 1.0865290068829891, "grad_norm": 8.418392181396484, "learning_rate": 1.913470993117011e-05, "loss": 0.3053, "step": 4420 }, { "epoch": 1.0889872173058013, "grad_norm": 5.659230709075928, "learning_rate": 1.9110127826941985e-05, "loss": 0.4282, "step": 4430 }, { "epoch": 1.0914454277286136, "grad_norm": 6.8115739822387695, "learning_rate": 1.9085545722713866e-05, "loss": 0.4113, "step": 4440 }, { "epoch": 1.0939036381514258, "grad_norm": 2.3417036533355713, "learning_rate": 1.9060963618485743e-05, "loss": 0.5599, "step": 4450 }, { "epoch": 1.096361848574238, "grad_norm": 11.404731750488281, "learning_rate": 1.903638151425762e-05, "loss": 0.4261, "step": 4460 }, { "epoch": 1.0988200589970503, "grad_norm": 11.112434387207031, "learning_rate": 1.9011799410029497e-05, "loss": 0.3985, "step": 4470 }, { "epoch": 1.1012782694198624, "grad_norm": 14.680532455444336, "learning_rate": 1.8987217305801378e-05, "loss": 0.4017, "step": 4480 }, { "epoch": 1.1037364798426745, "grad_norm": 9.73386287689209, "learning_rate": 1.8962635201573255e-05, "loss": 0.3909, "step": 4490 }, { "epoch": 1.1061946902654867, "grad_norm": 11.819046974182129, "learning_rate": 1.8938053097345135e-05, "loss": 0.4528, "step": 4500 }, { "epoch": 1.1086529006882988, "grad_norm": 6.53552770614624, "learning_rate": 1.891347099311701e-05, "loss": 0.5166, "step": 4510 }, { "epoch": 1.1111111111111112, "grad_norm": 7.795917987823486, "learning_rate": 1.888888888888889e-05, "loss": 0.3351, "step": 4520 }, { "epoch": 1.1135693215339233, "grad_norm": 6.816126823425293, "learning_rate": 1.8864306784660766e-05, "loss": 0.4847, "step": 4530 }, { "epoch": 1.1160275319567354, "grad_norm": 5.139041900634766, "learning_rate": 1.8839724680432647e-05, "loss": 0.4009, "step": 4540 }, { "epoch": 1.1184857423795478, "grad_norm": 12.780966758728027, "learning_rate": 1.8815142576204524e-05, "loss": 0.5058, "step": 4550 }, { "epoch": 1.12094395280236, "grad_norm": 8.147644996643066, "learning_rate": 1.87905604719764e-05, "loss": 0.325, "step": 4560 }, { "epoch": 1.123402163225172, "grad_norm": 2.919508457183838, "learning_rate": 1.8765978367748278e-05, "loss": 0.3701, "step": 4570 }, { "epoch": 1.1258603736479842, "grad_norm": 10.713155746459961, "learning_rate": 1.8741396263520158e-05, "loss": 0.3585, "step": 4580 }, { "epoch": 1.1283185840707965, "grad_norm": 9.912364959716797, "learning_rate": 1.8716814159292035e-05, "loss": 0.4552, "step": 4590 }, { "epoch": 1.1307767944936087, "grad_norm": 4.622004985809326, "learning_rate": 1.8692232055063916e-05, "loss": 0.3134, "step": 4600 }, { "epoch": 1.1332350049164208, "grad_norm": 14.282227516174316, "learning_rate": 1.8667649950835793e-05, "loss": 0.4462, "step": 4610 }, { "epoch": 1.135693215339233, "grad_norm": 9.701217651367188, "learning_rate": 1.864306784660767e-05, "loss": 0.4526, "step": 4620 }, { "epoch": 1.1381514257620453, "grad_norm": 9.643162727355957, "learning_rate": 1.8618485742379547e-05, "loss": 0.4688, "step": 4630 }, { "epoch": 1.1406096361848574, "grad_norm": 6.265407562255859, "learning_rate": 1.8593903638151427e-05, "loss": 0.443, "step": 4640 }, { "epoch": 1.1430678466076696, "grad_norm": 9.195865631103516, "learning_rate": 1.8569321533923304e-05, "loss": 0.3741, "step": 4650 }, { "epoch": 1.1455260570304817, "grad_norm": 3.8721189498901367, "learning_rate": 1.8544739429695185e-05, "loss": 0.4547, "step": 4660 }, { "epoch": 1.147984267453294, "grad_norm": 11.505948066711426, "learning_rate": 1.852015732546706e-05, "loss": 0.4096, "step": 4670 }, { "epoch": 1.1504424778761062, "grad_norm": 17.05303955078125, "learning_rate": 1.849557522123894e-05, "loss": 0.4285, "step": 4680 }, { "epoch": 1.1529006882989183, "grad_norm": 13.295167922973633, "learning_rate": 1.8470993117010816e-05, "loss": 0.3877, "step": 4690 }, { "epoch": 1.1553588987217305, "grad_norm": 3.7397992610931396, "learning_rate": 1.8446411012782696e-05, "loss": 0.3921, "step": 4700 }, { "epoch": 1.1578171091445428, "grad_norm": 6.389720439910889, "learning_rate": 1.8421828908554573e-05, "loss": 0.4433, "step": 4710 }, { "epoch": 1.160275319567355, "grad_norm": 16.336761474609375, "learning_rate": 1.839724680432645e-05, "loss": 0.3592, "step": 4720 }, { "epoch": 1.162733529990167, "grad_norm": 11.474458694458008, "learning_rate": 1.8372664700098328e-05, "loss": 0.4492, "step": 4730 }, { "epoch": 1.1651917404129795, "grad_norm": 14.184510231018066, "learning_rate": 1.8348082595870208e-05, "loss": 0.3927, "step": 4740 }, { "epoch": 1.1676499508357916, "grad_norm": 4.9853596687316895, "learning_rate": 1.8323500491642085e-05, "loss": 0.3645, "step": 4750 }, { "epoch": 1.1701081612586037, "grad_norm": 4.139890670776367, "learning_rate": 1.8298918387413965e-05, "loss": 0.5069, "step": 4760 }, { "epoch": 1.1725663716814159, "grad_norm": 7.539093971252441, "learning_rate": 1.827433628318584e-05, "loss": 0.3425, "step": 4770 }, { "epoch": 1.175024582104228, "grad_norm": 10.956673622131348, "learning_rate": 1.824975417895772e-05, "loss": 0.4965, "step": 4780 }, { "epoch": 1.1774827925270404, "grad_norm": 2.4851486682891846, "learning_rate": 1.8225172074729597e-05, "loss": 0.2776, "step": 4790 }, { "epoch": 1.1799410029498525, "grad_norm": 10.611666679382324, "learning_rate": 1.8200589970501477e-05, "loss": 0.4433, "step": 4800 }, { "epoch": 1.1823992133726646, "grad_norm": 11.952643394470215, "learning_rate": 1.8176007866273354e-05, "loss": 0.4683, "step": 4810 }, { "epoch": 1.184857423795477, "grad_norm": 2.9228858947753906, "learning_rate": 1.815142576204523e-05, "loss": 0.4132, "step": 4820 }, { "epoch": 1.1873156342182891, "grad_norm": 9.064404487609863, "learning_rate": 1.8126843657817108e-05, "loss": 0.2958, "step": 4830 }, { "epoch": 1.1897738446411013, "grad_norm": 11.08436107635498, "learning_rate": 1.810226155358899e-05, "loss": 0.2872, "step": 4840 }, { "epoch": 1.1922320550639134, "grad_norm": 18.37565803527832, "learning_rate": 1.8077679449360866e-05, "loss": 0.4896, "step": 4850 }, { "epoch": 1.1946902654867257, "grad_norm": 9.860465049743652, "learning_rate": 1.8053097345132746e-05, "loss": 0.4171, "step": 4860 }, { "epoch": 1.1971484759095379, "grad_norm": 18.63897132873535, "learning_rate": 1.8028515240904623e-05, "loss": 0.4581, "step": 4870 }, { "epoch": 1.19960668633235, "grad_norm": 9.42451000213623, "learning_rate": 1.80039331366765e-05, "loss": 0.31, "step": 4880 }, { "epoch": 1.2020648967551621, "grad_norm": 10.924408912658691, "learning_rate": 1.7979351032448377e-05, "loss": 0.4834, "step": 4890 }, { "epoch": 1.2045231071779745, "grad_norm": 6.614452838897705, "learning_rate": 1.7954768928220258e-05, "loss": 0.4819, "step": 4900 }, { "epoch": 1.2069813176007866, "grad_norm": 11.643143653869629, "learning_rate": 1.7930186823992135e-05, "loss": 0.402, "step": 4910 }, { "epoch": 1.2094395280235988, "grad_norm": 4.884191513061523, "learning_rate": 1.7905604719764015e-05, "loss": 0.411, "step": 4920 }, { "epoch": 1.2118977384464111, "grad_norm": 7.429741382598877, "learning_rate": 1.788102261553589e-05, "loss": 0.3273, "step": 4930 }, { "epoch": 1.2143559488692233, "grad_norm": 1.8154693841934204, "learning_rate": 1.785644051130777e-05, "loss": 0.3669, "step": 4940 }, { "epoch": 1.2168141592920354, "grad_norm": 11.316061973571777, "learning_rate": 1.7831858407079646e-05, "loss": 0.4333, "step": 4950 }, { "epoch": 1.2192723697148475, "grad_norm": 23.77151107788086, "learning_rate": 1.7807276302851527e-05, "loss": 0.4936, "step": 4960 }, { "epoch": 1.2217305801376597, "grad_norm": 18.95214080810547, "learning_rate": 1.7782694198623404e-05, "loss": 0.5011, "step": 4970 }, { "epoch": 1.224188790560472, "grad_norm": 12.412942886352539, "learning_rate": 1.7758112094395278e-05, "loss": 0.4451, "step": 4980 }, { "epoch": 1.2266470009832842, "grad_norm": 6.4491095542907715, "learning_rate": 1.7733529990167158e-05, "loss": 0.3611, "step": 4990 }, { "epoch": 1.2291052114060963, "grad_norm": 3.346402645111084, "learning_rate": 1.7708947885939035e-05, "loss": 0.4488, "step": 5000 }, { "epoch": 1.2315634218289087, "grad_norm": 8.305130958557129, "learning_rate": 1.7684365781710915e-05, "loss": 0.4574, "step": 5010 }, { "epoch": 1.2340216322517208, "grad_norm": 14.496387481689453, "learning_rate": 1.7659783677482793e-05, "loss": 0.4899, "step": 5020 }, { "epoch": 1.236479842674533, "grad_norm": 7.805213928222656, "learning_rate": 1.763520157325467e-05, "loss": 0.5002, "step": 5030 }, { "epoch": 1.238938053097345, "grad_norm": 8.615550994873047, "learning_rate": 1.7610619469026547e-05, "loss": 0.3966, "step": 5040 }, { "epoch": 1.2413962635201574, "grad_norm": 9.880414009094238, "learning_rate": 1.7586037364798427e-05, "loss": 0.4182, "step": 5050 }, { "epoch": 1.2438544739429696, "grad_norm": 4.006168842315674, "learning_rate": 1.7561455260570304e-05, "loss": 0.2903, "step": 5060 }, { "epoch": 1.2463126843657817, "grad_norm": 7.075710296630859, "learning_rate": 1.7536873156342185e-05, "loss": 0.4035, "step": 5070 }, { "epoch": 1.2487708947885938, "grad_norm": 5.246640682220459, "learning_rate": 1.751229105211406e-05, "loss": 0.3888, "step": 5080 }, { "epoch": 1.2512291052114062, "grad_norm": 8.475410461425781, "learning_rate": 1.748770894788594e-05, "loss": 0.4171, "step": 5090 }, { "epoch": 1.2536873156342183, "grad_norm": 11.207465171813965, "learning_rate": 1.7463126843657816e-05, "loss": 0.3227, "step": 5100 }, { "epoch": 1.2561455260570304, "grad_norm": 5.45085334777832, "learning_rate": 1.7438544739429696e-05, "loss": 0.2986, "step": 5110 }, { "epoch": 1.2586037364798428, "grad_norm": 5.72838020324707, "learning_rate": 1.7413962635201573e-05, "loss": 0.2916, "step": 5120 }, { "epoch": 1.261061946902655, "grad_norm": 9.054510116577148, "learning_rate": 1.7389380530973454e-05, "loss": 0.4479, "step": 5130 }, { "epoch": 1.263520157325467, "grad_norm": 5.517609119415283, "learning_rate": 1.7364798426745327e-05, "loss": 0.3562, "step": 5140 }, { "epoch": 1.2659783677482792, "grad_norm": 41.25855255126953, "learning_rate": 1.7340216322517208e-05, "loss": 0.477, "step": 5150 }, { "epoch": 1.2684365781710913, "grad_norm": 10.915813446044922, "learning_rate": 1.7315634218289085e-05, "loss": 0.3129, "step": 5160 }, { "epoch": 1.2708947885939037, "grad_norm": 7.620143890380859, "learning_rate": 1.7291052114060965e-05, "loss": 0.3244, "step": 5170 }, { "epoch": 1.2733529990167158, "grad_norm": 15.413076400756836, "learning_rate": 1.7266470009832842e-05, "loss": 0.3899, "step": 5180 }, { "epoch": 1.275811209439528, "grad_norm": 7.790799617767334, "learning_rate": 1.724188790560472e-05, "loss": 0.3127, "step": 5190 }, { "epoch": 1.2782694198623403, "grad_norm": 12.12572193145752, "learning_rate": 1.7217305801376596e-05, "loss": 0.5381, "step": 5200 }, { "epoch": 1.2807276302851525, "grad_norm": 12.057052612304688, "learning_rate": 1.7192723697148477e-05, "loss": 0.4055, "step": 5210 }, { "epoch": 1.2831858407079646, "grad_norm": 4.981482028961182, "learning_rate": 1.7168141592920354e-05, "loss": 0.4545, "step": 5220 }, { "epoch": 1.2856440511307767, "grad_norm": 7.928151607513428, "learning_rate": 1.7143559488692234e-05, "loss": 0.3191, "step": 5230 }, { "epoch": 1.2881022615535889, "grad_norm": 10.337085723876953, "learning_rate": 1.7118977384464108e-05, "loss": 0.2817, "step": 5240 }, { "epoch": 1.2905604719764012, "grad_norm": 12.059952735900879, "learning_rate": 1.709439528023599e-05, "loss": 0.4382, "step": 5250 }, { "epoch": 1.2930186823992134, "grad_norm": 5.851502418518066, "learning_rate": 1.7069813176007866e-05, "loss": 0.3125, "step": 5260 }, { "epoch": 1.2954768928220255, "grad_norm": 5.692627429962158, "learning_rate": 1.7045231071779746e-05, "loss": 0.367, "step": 5270 }, { "epoch": 1.2979351032448379, "grad_norm": 8.882339477539062, "learning_rate": 1.7020648967551623e-05, "loss": 0.5038, "step": 5280 }, { "epoch": 1.30039331366765, "grad_norm": 9.063218116760254, "learning_rate": 1.69960668633235e-05, "loss": 0.4004, "step": 5290 }, { "epoch": 1.3028515240904621, "grad_norm": 11.943826675415039, "learning_rate": 1.6971484759095377e-05, "loss": 0.4419, "step": 5300 }, { "epoch": 1.3053097345132743, "grad_norm": 6.683700084686279, "learning_rate": 1.6946902654867258e-05, "loss": 0.3526, "step": 5310 }, { "epoch": 1.3077679449360864, "grad_norm": 7.5174431800842285, "learning_rate": 1.6922320550639135e-05, "loss": 0.3931, "step": 5320 }, { "epoch": 1.3102261553588987, "grad_norm": 3.6929032802581787, "learning_rate": 1.6897738446411015e-05, "loss": 0.4803, "step": 5330 }, { "epoch": 1.3126843657817109, "grad_norm": 3.414058208465576, "learning_rate": 1.6873156342182892e-05, "loss": 0.333, "step": 5340 }, { "epoch": 1.315142576204523, "grad_norm": 8.907763481140137, "learning_rate": 1.684857423795477e-05, "loss": 0.4279, "step": 5350 }, { "epoch": 1.3176007866273354, "grad_norm": 7.825461387634277, "learning_rate": 1.6823992133726646e-05, "loss": 0.4313, "step": 5360 }, { "epoch": 1.3200589970501475, "grad_norm": 15.19956111907959, "learning_rate": 1.6799410029498527e-05, "loss": 0.3528, "step": 5370 }, { "epoch": 1.3225172074729596, "grad_norm": 14.31981086730957, "learning_rate": 1.6774827925270404e-05, "loss": 0.4271, "step": 5380 }, { "epoch": 1.324975417895772, "grad_norm": 11.376072883605957, "learning_rate": 1.6750245821042284e-05, "loss": 0.3928, "step": 5390 }, { "epoch": 1.3274336283185841, "grad_norm": 8.459187507629395, "learning_rate": 1.6725663716814158e-05, "loss": 0.4328, "step": 5400 }, { "epoch": 1.3298918387413963, "grad_norm": 9.353109359741211, "learning_rate": 1.6701081612586038e-05, "loss": 0.415, "step": 5410 }, { "epoch": 1.3323500491642084, "grad_norm": 4.807201862335205, "learning_rate": 1.6676499508357915e-05, "loss": 0.3736, "step": 5420 }, { "epoch": 1.3348082595870205, "grad_norm": 12.204873085021973, "learning_rate": 1.6651917404129796e-05, "loss": 0.3969, "step": 5430 }, { "epoch": 1.337266470009833, "grad_norm": 16.987590789794922, "learning_rate": 1.6627335299901673e-05, "loss": 0.4516, "step": 5440 }, { "epoch": 1.339724680432645, "grad_norm": 20.948518753051758, "learning_rate": 1.660275319567355e-05, "loss": 0.4578, "step": 5450 }, { "epoch": 1.3421828908554572, "grad_norm": 3.7863335609436035, "learning_rate": 1.6578171091445427e-05, "loss": 0.4538, "step": 5460 }, { "epoch": 1.3446411012782695, "grad_norm": 6.245743274688721, "learning_rate": 1.6553588987217307e-05, "loss": 0.3862, "step": 5470 }, { "epoch": 1.3470993117010817, "grad_norm": 3.955583333969116, "learning_rate": 1.6529006882989184e-05, "loss": 0.3472, "step": 5480 }, { "epoch": 1.3495575221238938, "grad_norm": 10.880657196044922, "learning_rate": 1.6504424778761065e-05, "loss": 0.3929, "step": 5490 }, { "epoch": 1.352015732546706, "grad_norm": 5.04379940032959, "learning_rate": 1.647984267453294e-05, "loss": 0.4552, "step": 5500 }, { "epoch": 1.354473942969518, "grad_norm": 6.873481273651123, "learning_rate": 1.645526057030482e-05, "loss": 0.416, "step": 5510 }, { "epoch": 1.3569321533923304, "grad_norm": 5.519433975219727, "learning_rate": 1.6430678466076696e-05, "loss": 0.3231, "step": 5520 }, { "epoch": 1.3593903638151426, "grad_norm": 4.904465675354004, "learning_rate": 1.6406096361848576e-05, "loss": 0.4412, "step": 5530 }, { "epoch": 1.3618485742379547, "grad_norm": 20.79932403564453, "learning_rate": 1.6381514257620453e-05, "loss": 0.3919, "step": 5540 }, { "epoch": 1.364306784660767, "grad_norm": 5.875002861022949, "learning_rate": 1.635693215339233e-05, "loss": 0.4119, "step": 5550 }, { "epoch": 1.3667649950835792, "grad_norm": 3.559235095977783, "learning_rate": 1.6332350049164208e-05, "loss": 0.3666, "step": 5560 }, { "epoch": 1.3692232055063913, "grad_norm": 7.156410217285156, "learning_rate": 1.6307767944936088e-05, "loss": 0.4035, "step": 5570 }, { "epoch": 1.3716814159292037, "grad_norm": 8.158479690551758, "learning_rate": 1.6283185840707965e-05, "loss": 0.371, "step": 5580 }, { "epoch": 1.3741396263520158, "grad_norm": 10.852849006652832, "learning_rate": 1.6258603736479846e-05, "loss": 0.2685, "step": 5590 }, { "epoch": 1.376597836774828, "grad_norm": 5.699408054351807, "learning_rate": 1.6234021632251723e-05, "loss": 0.4154, "step": 5600 }, { "epoch": 1.37905604719764, "grad_norm": 10.230939865112305, "learning_rate": 1.62094395280236e-05, "loss": 0.5255, "step": 5610 }, { "epoch": 1.3815142576204522, "grad_norm": 6.0074381828308105, "learning_rate": 1.6184857423795477e-05, "loss": 0.4159, "step": 5620 }, { "epoch": 1.3839724680432646, "grad_norm": 12.922666549682617, "learning_rate": 1.6160275319567357e-05, "loss": 0.4251, "step": 5630 }, { "epoch": 1.3864306784660767, "grad_norm": 4.792425155639648, "learning_rate": 1.6135693215339234e-05, "loss": 0.4955, "step": 5640 }, { "epoch": 1.3888888888888888, "grad_norm": 21.629932403564453, "learning_rate": 1.6111111111111115e-05, "loss": 0.4268, "step": 5650 }, { "epoch": 1.3913470993117012, "grad_norm": 3.594099521636963, "learning_rate": 1.6086529006882988e-05, "loss": 0.3127, "step": 5660 }, { "epoch": 1.3938053097345133, "grad_norm": 5.84594202041626, "learning_rate": 1.606194690265487e-05, "loss": 0.3695, "step": 5670 }, { "epoch": 1.3962635201573255, "grad_norm": 18.463998794555664, "learning_rate": 1.6037364798426746e-05, "loss": 0.4765, "step": 5680 }, { "epoch": 1.3987217305801376, "grad_norm": 9.709259986877441, "learning_rate": 1.6012782694198623e-05, "loss": 0.4274, "step": 5690 }, { "epoch": 1.4011799410029497, "grad_norm": 2.4493634700775146, "learning_rate": 1.5988200589970503e-05, "loss": 0.3226, "step": 5700 }, { "epoch": 1.403638151425762, "grad_norm": 5.552204132080078, "learning_rate": 1.5963618485742377e-05, "loss": 0.4234, "step": 5710 }, { "epoch": 1.4060963618485742, "grad_norm": 12.80062198638916, "learning_rate": 1.5939036381514257e-05, "loss": 0.4334, "step": 5720 }, { "epoch": 1.4085545722713864, "grad_norm": 7.245303153991699, "learning_rate": 1.5914454277286134e-05, "loss": 0.4346, "step": 5730 }, { "epoch": 1.4110127826941987, "grad_norm": 13.813474655151367, "learning_rate": 1.5889872173058015e-05, "loss": 0.3841, "step": 5740 }, { "epoch": 1.4134709931170109, "grad_norm": 2.4341657161712646, "learning_rate": 1.5865290068829892e-05, "loss": 0.4512, "step": 5750 }, { "epoch": 1.415929203539823, "grad_norm": 3.5993762016296387, "learning_rate": 1.584070796460177e-05, "loss": 0.3028, "step": 5760 }, { "epoch": 1.4183874139626351, "grad_norm": 7.188358306884766, "learning_rate": 1.5816125860373646e-05, "loss": 0.5075, "step": 5770 }, { "epoch": 1.4208456243854473, "grad_norm": 9.453777313232422, "learning_rate": 1.5791543756145526e-05, "loss": 0.4731, "step": 5780 }, { "epoch": 1.4233038348082596, "grad_norm": 9.14939022064209, "learning_rate": 1.5766961651917403e-05, "loss": 0.4976, "step": 5790 }, { "epoch": 1.4257620452310718, "grad_norm": 9.72834587097168, "learning_rate": 1.5742379547689284e-05, "loss": 0.4228, "step": 5800 }, { "epoch": 1.4282202556538839, "grad_norm": 8.499261856079102, "learning_rate": 1.571779744346116e-05, "loss": 0.476, "step": 5810 }, { "epoch": 1.4306784660766962, "grad_norm": 8.9592924118042, "learning_rate": 1.5693215339233038e-05, "loss": 0.3055, "step": 5820 }, { "epoch": 1.4331366764995084, "grad_norm": 10.471037864685059, "learning_rate": 1.5668633235004915e-05, "loss": 0.4094, "step": 5830 }, { "epoch": 1.4355948869223205, "grad_norm": 11.549220085144043, "learning_rate": 1.5644051130776796e-05, "loss": 0.4082, "step": 5840 }, { "epoch": 1.4380530973451329, "grad_norm": 7.28322696685791, "learning_rate": 1.5619469026548673e-05, "loss": 0.3888, "step": 5850 }, { "epoch": 1.440511307767945, "grad_norm": 9.803154945373535, "learning_rate": 1.5594886922320553e-05, "loss": 0.3862, "step": 5860 }, { "epoch": 1.4429695181907571, "grad_norm": 10.707706451416016, "learning_rate": 1.5570304818092427e-05, "loss": 0.3863, "step": 5870 }, { "epoch": 1.4454277286135693, "grad_norm": 8.8184175491333, "learning_rate": 1.5545722713864307e-05, "loss": 0.3073, "step": 5880 }, { "epoch": 1.4478859390363814, "grad_norm": 1.7422611713409424, "learning_rate": 1.5521140609636184e-05, "loss": 0.2473, "step": 5890 }, { "epoch": 1.4503441494591938, "grad_norm": 12.162628173828125, "learning_rate": 1.5496558505408065e-05, "loss": 0.5383, "step": 5900 }, { "epoch": 1.452802359882006, "grad_norm": 1.4871968030929565, "learning_rate": 1.547197640117994e-05, "loss": 0.2758, "step": 5910 }, { "epoch": 1.455260570304818, "grad_norm": 11.46398639678955, "learning_rate": 1.544739429695182e-05, "loss": 0.2833, "step": 5920 }, { "epoch": 1.4577187807276304, "grad_norm": 1.0898629426956177, "learning_rate": 1.5422812192723696e-05, "loss": 0.4378, "step": 5930 }, { "epoch": 1.4601769911504425, "grad_norm": 12.882427215576172, "learning_rate": 1.5398230088495576e-05, "loss": 0.3782, "step": 5940 }, { "epoch": 1.4626352015732547, "grad_norm": 10.144386291503906, "learning_rate": 1.5373647984267453e-05, "loss": 0.4062, "step": 5950 }, { "epoch": 1.4650934119960668, "grad_norm": 14.940133094787598, "learning_rate": 1.5349065880039334e-05, "loss": 0.3152, "step": 5960 }, { "epoch": 1.467551622418879, "grad_norm": 4.6012468338012695, "learning_rate": 1.5324483775811207e-05, "loss": 0.5087, "step": 5970 }, { "epoch": 1.4700098328416913, "grad_norm": 8.861075401306152, "learning_rate": 1.5299901671583088e-05, "loss": 0.3727, "step": 5980 }, { "epoch": 1.4724680432645034, "grad_norm": 10.086342811584473, "learning_rate": 1.5275319567354965e-05, "loss": 0.432, "step": 5990 }, { "epoch": 1.4749262536873156, "grad_norm": 17.717960357666016, "learning_rate": 1.5250737463126845e-05, "loss": 0.5225, "step": 6000 }, { "epoch": 1.477384464110128, "grad_norm": 4.808421611785889, "learning_rate": 1.522615535889872e-05, "loss": 0.3448, "step": 6010 }, { "epoch": 1.47984267453294, "grad_norm": 5.139224529266357, "learning_rate": 1.5201573254670601e-05, "loss": 0.366, "step": 6020 }, { "epoch": 1.4823008849557522, "grad_norm": 3.4996519088745117, "learning_rate": 1.5176991150442478e-05, "loss": 0.2915, "step": 6030 }, { "epoch": 1.4847590953785645, "grad_norm": 13.536445617675781, "learning_rate": 1.5152409046214357e-05, "loss": 0.4655, "step": 6040 }, { "epoch": 1.4872173058013767, "grad_norm": 9.212183952331543, "learning_rate": 1.5127826941986234e-05, "loss": 0.3053, "step": 6050 }, { "epoch": 1.4896755162241888, "grad_norm": 7.971109390258789, "learning_rate": 1.5103244837758113e-05, "loss": 0.4979, "step": 6060 }, { "epoch": 1.492133726647001, "grad_norm": 9.93220043182373, "learning_rate": 1.507866273352999e-05, "loss": 0.438, "step": 6070 }, { "epoch": 1.494591937069813, "grad_norm": 8.826542854309082, "learning_rate": 1.505408062930187e-05, "loss": 0.4447, "step": 6080 }, { "epoch": 1.4970501474926254, "grad_norm": 9.936312675476074, "learning_rate": 1.5029498525073746e-05, "loss": 0.4404, "step": 6090 }, { "epoch": 1.4995083579154376, "grad_norm": 12.181827545166016, "learning_rate": 1.5004916420845626e-05, "loss": 0.4187, "step": 6100 }, { "epoch": 1.5019665683382497, "grad_norm": 9.074667930603027, "learning_rate": 1.4980334316617501e-05, "loss": 0.3528, "step": 6110 }, { "epoch": 1.504424778761062, "grad_norm": 5.361248970031738, "learning_rate": 1.495575221238938e-05, "loss": 0.295, "step": 6120 }, { "epoch": 1.506882989183874, "grad_norm": 4.177809715270996, "learning_rate": 1.4931170108161259e-05, "loss": 0.5698, "step": 6130 }, { "epoch": 1.5093411996066863, "grad_norm": 5.42146635055542, "learning_rate": 1.4906588003933136e-05, "loss": 0.2622, "step": 6140 }, { "epoch": 1.5117994100294987, "grad_norm": 25.01091957092285, "learning_rate": 1.4882005899705015e-05, "loss": 0.3905, "step": 6150 }, { "epoch": 1.5142576204523106, "grad_norm": 10.310868263244629, "learning_rate": 1.4857423795476893e-05, "loss": 0.2842, "step": 6160 }, { "epoch": 1.516715830875123, "grad_norm": 6.5444254875183105, "learning_rate": 1.483284169124877e-05, "loss": 0.505, "step": 6170 }, { "epoch": 1.519174041297935, "grad_norm": 5.236999988555908, "learning_rate": 1.480825958702065e-05, "loss": 0.3311, "step": 6180 }, { "epoch": 1.5216322517207472, "grad_norm": 10.419346809387207, "learning_rate": 1.4783677482792526e-05, "loss": 0.4586, "step": 6190 }, { "epoch": 1.5240904621435596, "grad_norm": 7.350751876831055, "learning_rate": 1.4759095378564405e-05, "loss": 0.4314, "step": 6200 }, { "epoch": 1.5265486725663717, "grad_norm": 6.0221452713012695, "learning_rate": 1.4734513274336284e-05, "loss": 0.311, "step": 6210 }, { "epoch": 1.5290068829891839, "grad_norm": 6.613132476806641, "learning_rate": 1.470993117010816e-05, "loss": 0.3642, "step": 6220 }, { "epoch": 1.5314650934119962, "grad_norm": 4.829579830169678, "learning_rate": 1.468534906588004e-05, "loss": 0.3123, "step": 6230 }, { "epoch": 1.5339233038348081, "grad_norm": 15.385251998901367, "learning_rate": 1.4660766961651918e-05, "loss": 0.3225, "step": 6240 }, { "epoch": 1.5363815142576205, "grad_norm": 11.137362480163574, "learning_rate": 1.4636184857423795e-05, "loss": 0.5059, "step": 6250 }, { "epoch": 1.5388397246804326, "grad_norm": 9.528539657592773, "learning_rate": 1.4611602753195674e-05, "loss": 0.3612, "step": 6260 }, { "epoch": 1.5412979351032448, "grad_norm": 4.1244401931762695, "learning_rate": 1.4587020648967551e-05, "loss": 0.3912, "step": 6270 }, { "epoch": 1.543756145526057, "grad_norm": 6.008029460906982, "learning_rate": 1.456243854473943e-05, "loss": 0.2935, "step": 6280 }, { "epoch": 1.5462143559488692, "grad_norm": 10.341638565063477, "learning_rate": 1.4537856440511309e-05, "loss": 0.4434, "step": 6290 }, { "epoch": 1.5486725663716814, "grad_norm": 7.740987777709961, "learning_rate": 1.4513274336283186e-05, "loss": 0.4178, "step": 6300 }, { "epoch": 1.5511307767944937, "grad_norm": 9.332296371459961, "learning_rate": 1.4488692232055064e-05, "loss": 0.4098, "step": 6310 }, { "epoch": 1.5535889872173057, "grad_norm": 8.284363746643066, "learning_rate": 1.4464110127826941e-05, "loss": 0.4091, "step": 6320 }, { "epoch": 1.556047197640118, "grad_norm": 9.545183181762695, "learning_rate": 1.443952802359882e-05, "loss": 0.3574, "step": 6330 }, { "epoch": 1.5585054080629301, "grad_norm": 3.6961607933044434, "learning_rate": 1.4414945919370699e-05, "loss": 0.346, "step": 6340 }, { "epoch": 1.5609636184857423, "grad_norm": 11.243683815002441, "learning_rate": 1.4390363815142576e-05, "loss": 0.4765, "step": 6350 }, { "epoch": 1.5634218289085546, "grad_norm": 11.736071586608887, "learning_rate": 1.4365781710914455e-05, "loss": 0.3102, "step": 6360 }, { "epoch": 1.5658800393313668, "grad_norm": 11.394797325134277, "learning_rate": 1.4341199606686333e-05, "loss": 0.4895, "step": 6370 }, { "epoch": 1.568338249754179, "grad_norm": 11.11750602722168, "learning_rate": 1.431661750245821e-05, "loss": 0.4211, "step": 6380 }, { "epoch": 1.5707964601769913, "grad_norm": 5.133919715881348, "learning_rate": 1.429203539823009e-05, "loss": 0.3813, "step": 6390 }, { "epoch": 1.5732546705998034, "grad_norm": 4.457335472106934, "learning_rate": 1.4267453294001966e-05, "loss": 0.303, "step": 6400 }, { "epoch": 1.5757128810226155, "grad_norm": 6.312507152557373, "learning_rate": 1.4242871189773845e-05, "loss": 0.4825, "step": 6410 }, { "epoch": 1.5781710914454279, "grad_norm": 11.91999626159668, "learning_rate": 1.4218289085545724e-05, "loss": 0.3497, "step": 6420 }, { "epoch": 1.5806293018682398, "grad_norm": 8.295093536376953, "learning_rate": 1.4193706981317601e-05, "loss": 0.4626, "step": 6430 }, { "epoch": 1.5830875122910522, "grad_norm": 9.615830421447754, "learning_rate": 1.416912487708948e-05, "loss": 0.5813, "step": 6440 }, { "epoch": 1.5855457227138643, "grad_norm": 7.082546234130859, "learning_rate": 1.4144542772861357e-05, "loss": 0.4535, "step": 6450 }, { "epoch": 1.5880039331366764, "grad_norm": 4.20911169052124, "learning_rate": 1.4119960668633235e-05, "loss": 0.3478, "step": 6460 }, { "epoch": 1.5904621435594888, "grad_norm": 10.30086612701416, "learning_rate": 1.4095378564405114e-05, "loss": 0.1913, "step": 6470 }, { "epoch": 1.592920353982301, "grad_norm": 11.328630447387695, "learning_rate": 1.4070796460176991e-05, "loss": 0.4691, "step": 6480 }, { "epoch": 1.595378564405113, "grad_norm": 18.686323165893555, "learning_rate": 1.404621435594887e-05, "loss": 0.3684, "step": 6490 }, { "epoch": 1.5978367748279254, "grad_norm": 12.687962532043457, "learning_rate": 1.4021632251720749e-05, "loss": 0.421, "step": 6500 }, { "epoch": 1.6002949852507373, "grad_norm": 11.840784072875977, "learning_rate": 1.3997050147492626e-05, "loss": 0.438, "step": 6510 }, { "epoch": 1.6027531956735497, "grad_norm": 7.867887020111084, "learning_rate": 1.3972468043264505e-05, "loss": 0.5168, "step": 6520 }, { "epoch": 1.6052114060963618, "grad_norm": 8.438105583190918, "learning_rate": 1.3947885939036382e-05, "loss": 0.3778, "step": 6530 }, { "epoch": 1.607669616519174, "grad_norm": 7.61447811126709, "learning_rate": 1.392330383480826e-05, "loss": 0.3164, "step": 6540 }, { "epoch": 1.6101278269419863, "grad_norm": 10.340341567993164, "learning_rate": 1.3898721730580139e-05, "loss": 0.3181, "step": 6550 }, { "epoch": 1.6125860373647984, "grad_norm": 8.937304496765137, "learning_rate": 1.3874139626352016e-05, "loss": 0.5963, "step": 6560 }, { "epoch": 1.6150442477876106, "grad_norm": 9.980753898620605, "learning_rate": 1.3849557522123895e-05, "loss": 0.3389, "step": 6570 }, { "epoch": 1.617502458210423, "grad_norm": 7.966772556304932, "learning_rate": 1.3824975417895772e-05, "loss": 0.489, "step": 6580 }, { "epoch": 1.6199606686332348, "grad_norm": 10.203620910644531, "learning_rate": 1.380039331366765e-05, "loss": 0.4598, "step": 6590 }, { "epoch": 1.6224188790560472, "grad_norm": 6.172760009765625, "learning_rate": 1.377581120943953e-05, "loss": 0.3437, "step": 6600 }, { "epoch": 1.6248770894788593, "grad_norm": 11.496180534362793, "learning_rate": 1.3751229105211406e-05, "loss": 0.3206, "step": 6610 }, { "epoch": 1.6273352999016715, "grad_norm": 8.176165580749512, "learning_rate": 1.3726647000983285e-05, "loss": 0.3896, "step": 6620 }, { "epoch": 1.6297935103244838, "grad_norm": 14.373556137084961, "learning_rate": 1.3702064896755164e-05, "loss": 0.4, "step": 6630 }, { "epoch": 1.632251720747296, "grad_norm": 11.034965515136719, "learning_rate": 1.3677482792527041e-05, "loss": 0.4018, "step": 6640 }, { "epoch": 1.634709931170108, "grad_norm": 11.679769515991211, "learning_rate": 1.365290068829892e-05, "loss": 0.3173, "step": 6650 }, { "epoch": 1.6371681415929205, "grad_norm": 9.429061889648438, "learning_rate": 1.3628318584070797e-05, "loss": 0.3021, "step": 6660 }, { "epoch": 1.6396263520157326, "grad_norm": 9.269270896911621, "learning_rate": 1.3603736479842676e-05, "loss": 0.3703, "step": 6670 }, { "epoch": 1.6420845624385447, "grad_norm": 7.47467565536499, "learning_rate": 1.3579154375614554e-05, "loss": 0.4222, "step": 6680 }, { "epoch": 1.644542772861357, "grad_norm": 5.367368221282959, "learning_rate": 1.3554572271386431e-05, "loss": 0.446, "step": 6690 }, { "epoch": 1.647000983284169, "grad_norm": 13.329296112060547, "learning_rate": 1.352999016715831e-05, "loss": 0.4221, "step": 6700 }, { "epoch": 1.6494591937069814, "grad_norm": 7.237957000732422, "learning_rate": 1.3505408062930187e-05, "loss": 0.3477, "step": 6710 }, { "epoch": 1.6519174041297935, "grad_norm": 5.3150248527526855, "learning_rate": 1.3480825958702066e-05, "loss": 0.4208, "step": 6720 }, { "epoch": 1.6543756145526056, "grad_norm": 16.04496955871582, "learning_rate": 1.3456243854473945e-05, "loss": 0.3181, "step": 6730 }, { "epoch": 1.656833824975418, "grad_norm": 9.493232727050781, "learning_rate": 1.3431661750245822e-05, "loss": 0.4005, "step": 6740 }, { "epoch": 1.6592920353982301, "grad_norm": 7.157200813293457, "learning_rate": 1.3407079646017699e-05, "loss": 0.4872, "step": 6750 }, { "epoch": 1.6617502458210422, "grad_norm": 10.452499389648438, "learning_rate": 1.3382497541789577e-05, "loss": 0.3943, "step": 6760 }, { "epoch": 1.6642084562438546, "grad_norm": 5.284028053283691, "learning_rate": 1.3357915437561455e-05, "loss": 0.4028, "step": 6770 }, { "epoch": 1.6666666666666665, "grad_norm": 6.920553684234619, "learning_rate": 1.3333333333333333e-05, "loss": 0.2819, "step": 6780 }, { "epoch": 1.6691248770894789, "grad_norm": 5.611143589019775, "learning_rate": 1.330875122910521e-05, "loss": 0.2865, "step": 6790 }, { "epoch": 1.671583087512291, "grad_norm": 10.037906646728516, "learning_rate": 1.3284169124877089e-05, "loss": 0.3897, "step": 6800 }, { "epoch": 1.6740412979351031, "grad_norm": 8.229888916015625, "learning_rate": 1.3259587020648968e-05, "loss": 0.5116, "step": 6810 }, { "epoch": 1.6764995083579155, "grad_norm": 2.994560956954956, "learning_rate": 1.3235004916420845e-05, "loss": 0.4533, "step": 6820 }, { "epoch": 1.6789577187807276, "grad_norm": 5.300467014312744, "learning_rate": 1.3210422812192724e-05, "loss": 0.4413, "step": 6830 }, { "epoch": 1.6814159292035398, "grad_norm": 8.629834175109863, "learning_rate": 1.31858407079646e-05, "loss": 0.428, "step": 6840 }, { "epoch": 1.6838741396263521, "grad_norm": 5.696138381958008, "learning_rate": 1.316125860373648e-05, "loss": 0.3433, "step": 6850 }, { "epoch": 1.6863323500491643, "grad_norm": 12.302641868591309, "learning_rate": 1.3136676499508358e-05, "loss": 0.3639, "step": 6860 }, { "epoch": 1.6887905604719764, "grad_norm": 13.657188415527344, "learning_rate": 1.3112094395280235e-05, "loss": 0.5504, "step": 6870 }, { "epoch": 1.6912487708947888, "grad_norm": 9.680416107177734, "learning_rate": 1.3087512291052114e-05, "loss": 0.4281, "step": 6880 }, { "epoch": 1.6937069813176007, "grad_norm": 9.07966136932373, "learning_rate": 1.3062930186823993e-05, "loss": 0.4077, "step": 6890 }, { "epoch": 1.696165191740413, "grad_norm": 6.182389259338379, "learning_rate": 1.303834808259587e-05, "loss": 0.3112, "step": 6900 }, { "epoch": 1.6986234021632252, "grad_norm": 25.305696487426758, "learning_rate": 1.3013765978367749e-05, "loss": 0.465, "step": 6910 }, { "epoch": 1.7010816125860373, "grad_norm": 6.8333740234375, "learning_rate": 1.2989183874139626e-05, "loss": 0.2806, "step": 6920 }, { "epoch": 1.7035398230088497, "grad_norm": 4.880908012390137, "learning_rate": 1.2964601769911504e-05, "loss": 0.3752, "step": 6930 }, { "epoch": 1.7059980334316618, "grad_norm": 6.360934257507324, "learning_rate": 1.2940019665683383e-05, "loss": 0.4239, "step": 6940 }, { "epoch": 1.708456243854474, "grad_norm": 6.746744155883789, "learning_rate": 1.291543756145526e-05, "loss": 0.32, "step": 6950 }, { "epoch": 1.7109144542772863, "grad_norm": 12.636385917663574, "learning_rate": 1.2890855457227139e-05, "loss": 0.4338, "step": 6960 }, { "epoch": 1.7133726647000982, "grad_norm": 14.079647064208984, "learning_rate": 1.2866273352999016e-05, "loss": 0.598, "step": 6970 }, { "epoch": 1.7158308751229105, "grad_norm": 5.760141372680664, "learning_rate": 1.2841691248770895e-05, "loss": 0.2912, "step": 6980 }, { "epoch": 1.7182890855457227, "grad_norm": 10.4988431930542, "learning_rate": 1.2817109144542773e-05, "loss": 0.3809, "step": 6990 }, { "epoch": 1.7207472959685348, "grad_norm": 9.045525550842285, "learning_rate": 1.279252704031465e-05, "loss": 0.2428, "step": 7000 }, { "epoch": 1.7232055063913472, "grad_norm": 10.693390846252441, "learning_rate": 1.276794493608653e-05, "loss": 0.3202, "step": 7010 }, { "epoch": 1.7256637168141593, "grad_norm": 5.125523090362549, "learning_rate": 1.2743362831858408e-05, "loss": 0.4035, "step": 7020 }, { "epoch": 1.7281219272369714, "grad_norm": 9.755571365356445, "learning_rate": 1.2718780727630285e-05, "loss": 0.3554, "step": 7030 }, { "epoch": 1.7305801376597838, "grad_norm": 2.1122326850891113, "learning_rate": 1.2694198623402164e-05, "loss": 0.5691, "step": 7040 }, { "epoch": 1.7330383480825957, "grad_norm": 15.664355278015137, "learning_rate": 1.266961651917404e-05, "loss": 0.5097, "step": 7050 }, { "epoch": 1.735496558505408, "grad_norm": 14.100229263305664, "learning_rate": 1.264503441494592e-05, "loss": 0.4259, "step": 7060 }, { "epoch": 1.7379547689282202, "grad_norm": 10.935966491699219, "learning_rate": 1.2620452310717798e-05, "loss": 0.274, "step": 7070 }, { "epoch": 1.7404129793510323, "grad_norm": 6.672271728515625, "learning_rate": 1.2595870206489675e-05, "loss": 0.3258, "step": 7080 }, { "epoch": 1.7428711897738447, "grad_norm": 7.128734588623047, "learning_rate": 1.2571288102261554e-05, "loss": 0.4627, "step": 7090 }, { "epoch": 1.7453294001966568, "grad_norm": 6.704835891723633, "learning_rate": 1.2546705998033431e-05, "loss": 0.3312, "step": 7100 }, { "epoch": 1.747787610619469, "grad_norm": 4.882321834564209, "learning_rate": 1.252212389380531e-05, "loss": 0.3735, "step": 7110 }, { "epoch": 1.7502458210422813, "grad_norm": 31.229286193847656, "learning_rate": 1.2497541789577189e-05, "loss": 0.362, "step": 7120 }, { "epoch": 1.7527040314650935, "grad_norm": 10.265987396240234, "learning_rate": 1.2472959685349066e-05, "loss": 0.357, "step": 7130 }, { "epoch": 1.7551622418879056, "grad_norm": 7.587973594665527, "learning_rate": 1.2448377581120944e-05, "loss": 0.3675, "step": 7140 }, { "epoch": 1.757620452310718, "grad_norm": 7.590911388397217, "learning_rate": 1.2423795476892823e-05, "loss": 0.4524, "step": 7150 }, { "epoch": 1.7600786627335299, "grad_norm": 14.100318908691406, "learning_rate": 1.23992133726647e-05, "loss": 0.3755, "step": 7160 }, { "epoch": 1.7625368731563422, "grad_norm": 3.271604537963867, "learning_rate": 1.2374631268436579e-05, "loss": 0.2872, "step": 7170 }, { "epoch": 1.7649950835791544, "grad_norm": 8.690317153930664, "learning_rate": 1.2350049164208456e-05, "loss": 0.4683, "step": 7180 }, { "epoch": 1.7674532940019665, "grad_norm": 10.508160591125488, "learning_rate": 1.2325467059980335e-05, "loss": 0.3983, "step": 7190 }, { "epoch": 1.7699115044247788, "grad_norm": 7.1707963943481445, "learning_rate": 1.2300884955752214e-05, "loss": 0.314, "step": 7200 }, { "epoch": 1.772369714847591, "grad_norm": 9.432787895202637, "learning_rate": 1.227630285152409e-05, "loss": 0.3655, "step": 7210 }, { "epoch": 1.7748279252704031, "grad_norm": 4.761153697967529, "learning_rate": 1.225172074729597e-05, "loss": 0.5864, "step": 7220 }, { "epoch": 1.7772861356932155, "grad_norm": 5.6719865798950195, "learning_rate": 1.2227138643067848e-05, "loss": 0.3339, "step": 7230 }, { "epoch": 1.7797443461160274, "grad_norm": 8.002032279968262, "learning_rate": 1.2202556538839725e-05, "loss": 0.3922, "step": 7240 }, { "epoch": 1.7822025565388397, "grad_norm": 8.651975631713867, "learning_rate": 1.2177974434611604e-05, "loss": 0.449, "step": 7250 }, { "epoch": 1.7846607669616519, "grad_norm": 11.270854949951172, "learning_rate": 1.2153392330383481e-05, "loss": 0.292, "step": 7260 }, { "epoch": 1.787118977384464, "grad_norm": 10.927766799926758, "learning_rate": 1.212881022615536e-05, "loss": 0.4603, "step": 7270 }, { "epoch": 1.7895771878072764, "grad_norm": 8.29560375213623, "learning_rate": 1.2104228121927238e-05, "loss": 0.4571, "step": 7280 }, { "epoch": 1.7920353982300885, "grad_norm": 9.969430923461914, "learning_rate": 1.2079646017699115e-05, "loss": 0.4208, "step": 7290 }, { "epoch": 1.7944936086529006, "grad_norm": 9.935297012329102, "learning_rate": 1.2055063913470994e-05, "loss": 0.407, "step": 7300 }, { "epoch": 1.796951819075713, "grad_norm": 8.315773010253906, "learning_rate": 1.2030481809242871e-05, "loss": 0.463, "step": 7310 }, { "epoch": 1.799410029498525, "grad_norm": 16.16525650024414, "learning_rate": 1.200589970501475e-05, "loss": 0.3611, "step": 7320 }, { "epoch": 1.8018682399213373, "grad_norm": 13.66059398651123, "learning_rate": 1.1981317600786629e-05, "loss": 0.4282, "step": 7330 }, { "epoch": 1.8043264503441496, "grad_norm": 3.638113021850586, "learning_rate": 1.1956735496558506e-05, "loss": 0.3613, "step": 7340 }, { "epoch": 1.8067846607669615, "grad_norm": 11.922338485717773, "learning_rate": 1.1932153392330385e-05, "loss": 0.38, "step": 7350 }, { "epoch": 1.809242871189774, "grad_norm": 13.002695083618164, "learning_rate": 1.1907571288102263e-05, "loss": 0.3608, "step": 7360 }, { "epoch": 1.811701081612586, "grad_norm": 4.156497478485107, "learning_rate": 1.188298918387414e-05, "loss": 0.4063, "step": 7370 }, { "epoch": 1.8141592920353982, "grad_norm": 4.430566787719727, "learning_rate": 1.1858407079646019e-05, "loss": 0.4085, "step": 7380 }, { "epoch": 1.8166175024582105, "grad_norm": 8.262622833251953, "learning_rate": 1.1833824975417896e-05, "loss": 0.3649, "step": 7390 }, { "epoch": 1.8190757128810227, "grad_norm": 5.807417392730713, "learning_rate": 1.1809242871189775e-05, "loss": 0.3206, "step": 7400 }, { "epoch": 1.8215339233038348, "grad_norm": 9.102004051208496, "learning_rate": 1.1784660766961654e-05, "loss": 0.3436, "step": 7410 }, { "epoch": 1.8239921337266471, "grad_norm": 12.338142395019531, "learning_rate": 1.176007866273353e-05, "loss": 0.376, "step": 7420 }, { "epoch": 1.826450344149459, "grad_norm": 9.166077613830566, "learning_rate": 1.173549655850541e-05, "loss": 0.4804, "step": 7430 }, { "epoch": 1.8289085545722714, "grad_norm": 9.355168342590332, "learning_rate": 1.1710914454277286e-05, "loss": 0.4607, "step": 7440 }, { "epoch": 1.8313667649950836, "grad_norm": 16.249420166015625, "learning_rate": 1.1686332350049165e-05, "loss": 0.3383, "step": 7450 }, { "epoch": 1.8338249754178957, "grad_norm": 9.328553199768066, "learning_rate": 1.1661750245821042e-05, "loss": 0.3955, "step": 7460 }, { "epoch": 1.836283185840708, "grad_norm": 8.066047668457031, "learning_rate": 1.163716814159292e-05, "loss": 0.4469, "step": 7470 }, { "epoch": 1.8387413962635202, "grad_norm": 10.128920555114746, "learning_rate": 1.1612586037364798e-05, "loss": 0.4607, "step": 7480 }, { "epoch": 1.8411996066863323, "grad_norm": 4.772175312042236, "learning_rate": 1.1588003933136677e-05, "loss": 0.4581, "step": 7490 }, { "epoch": 1.8436578171091447, "grad_norm": 5.528618335723877, "learning_rate": 1.1563421828908554e-05, "loss": 0.3219, "step": 7500 }, { "epoch": 1.8461160275319566, "grad_norm": 7.458261013031006, "learning_rate": 1.1538839724680433e-05, "loss": 0.368, "step": 7510 }, { "epoch": 1.848574237954769, "grad_norm": 5.45689058303833, "learning_rate": 1.151425762045231e-05, "loss": 0.3636, "step": 7520 }, { "epoch": 1.851032448377581, "grad_norm": 9.244267463684082, "learning_rate": 1.1489675516224188e-05, "loss": 0.3186, "step": 7530 }, { "epoch": 1.8534906588003932, "grad_norm": 9.342634201049805, "learning_rate": 1.1465093411996067e-05, "loss": 0.5279, "step": 7540 }, { "epoch": 1.8559488692232056, "grad_norm": 3.6880886554718018, "learning_rate": 1.1440511307767944e-05, "loss": 0.3658, "step": 7550 }, { "epoch": 1.8584070796460177, "grad_norm": 5.906849384307861, "learning_rate": 1.1415929203539823e-05, "loss": 0.54, "step": 7560 }, { "epoch": 1.8608652900688298, "grad_norm": 9.609719276428223, "learning_rate": 1.13913470993117e-05, "loss": 0.4203, "step": 7570 }, { "epoch": 1.8633235004916422, "grad_norm": 14.703213691711426, "learning_rate": 1.1366764995083579e-05, "loss": 0.3949, "step": 7580 }, { "epoch": 1.8657817109144543, "grad_norm": 8.16911792755127, "learning_rate": 1.1342182890855458e-05, "loss": 0.387, "step": 7590 }, { "epoch": 1.8682399213372665, "grad_norm": 13.227580070495605, "learning_rate": 1.1317600786627335e-05, "loss": 0.4303, "step": 7600 }, { "epoch": 1.8706981317600788, "grad_norm": 4.321247100830078, "learning_rate": 1.1293018682399213e-05, "loss": 0.2968, "step": 7610 }, { "epoch": 1.8731563421828907, "grad_norm": 6.535560131072998, "learning_rate": 1.1268436578171092e-05, "loss": 0.4282, "step": 7620 }, { "epoch": 1.875614552605703, "grad_norm": 12.690583229064941, "learning_rate": 1.1243854473942969e-05, "loss": 0.4442, "step": 7630 }, { "epoch": 1.8780727630285152, "grad_norm": 9.127006530761719, "learning_rate": 1.1219272369714848e-05, "loss": 0.4619, "step": 7640 }, { "epoch": 1.8805309734513274, "grad_norm": 20.811914443969727, "learning_rate": 1.1194690265486725e-05, "loss": 0.3939, "step": 7650 }, { "epoch": 1.8829891838741397, "grad_norm": 1.1773931980133057, "learning_rate": 1.1170108161258604e-05, "loss": 0.3284, "step": 7660 }, { "epoch": 1.8854473942969519, "grad_norm": 14.679533004760742, "learning_rate": 1.1145526057030482e-05, "loss": 0.437, "step": 7670 }, { "epoch": 1.887905604719764, "grad_norm": 7.121145248413086, "learning_rate": 1.112094395280236e-05, "loss": 0.4226, "step": 7680 }, { "epoch": 1.8903638151425763, "grad_norm": 9.137502670288086, "learning_rate": 1.1096361848574238e-05, "loss": 0.4453, "step": 7690 }, { "epoch": 1.8928220255653883, "grad_norm": 3.1821608543395996, "learning_rate": 1.1071779744346115e-05, "loss": 0.3086, "step": 7700 }, { "epoch": 1.8952802359882006, "grad_norm": 7.363341808319092, "learning_rate": 1.1047197640117994e-05, "loss": 0.3885, "step": 7710 }, { "epoch": 1.8977384464110127, "grad_norm": 5.6837849617004395, "learning_rate": 1.1022615535889873e-05, "loss": 0.3716, "step": 7720 }, { "epoch": 1.9001966568338249, "grad_norm": 9.409944534301758, "learning_rate": 1.099803343166175e-05, "loss": 0.4026, "step": 7730 }, { "epoch": 1.9026548672566372, "grad_norm": 10.059317588806152, "learning_rate": 1.0973451327433629e-05, "loss": 0.4067, "step": 7740 }, { "epoch": 1.9051130776794494, "grad_norm": 6.719808101654053, "learning_rate": 1.0948869223205507e-05, "loss": 0.2886, "step": 7750 }, { "epoch": 1.9075712881022615, "grad_norm": 10.334959030151367, "learning_rate": 1.0924287118977384e-05, "loss": 0.3885, "step": 7760 }, { "epoch": 1.9100294985250739, "grad_norm": 4.672759056091309, "learning_rate": 1.0899705014749263e-05, "loss": 0.4876, "step": 7770 }, { "epoch": 1.9124877089478858, "grad_norm": 10.332815170288086, "learning_rate": 1.087512291052114e-05, "loss": 0.3283, "step": 7780 }, { "epoch": 1.9149459193706981, "grad_norm": 11.761624336242676, "learning_rate": 1.0850540806293019e-05, "loss": 0.3182, "step": 7790 }, { "epoch": 1.9174041297935103, "grad_norm": 8.998651504516602, "learning_rate": 1.0825958702064898e-05, "loss": 0.3589, "step": 7800 }, { "epoch": 1.9198623402163224, "grad_norm": 6.574552536010742, "learning_rate": 1.0801376597836775e-05, "loss": 0.3865, "step": 7810 }, { "epoch": 1.9223205506391348, "grad_norm": 8.61694622039795, "learning_rate": 1.0776794493608653e-05, "loss": 0.4595, "step": 7820 }, { "epoch": 1.924778761061947, "grad_norm": 19.831283569335938, "learning_rate": 1.075221238938053e-05, "loss": 0.4832, "step": 7830 }, { "epoch": 1.927236971484759, "grad_norm": 10.715694427490234, "learning_rate": 1.072763028515241e-05, "loss": 0.3604, "step": 7840 }, { "epoch": 1.9296951819075714, "grad_norm": 15.424195289611816, "learning_rate": 1.0703048180924288e-05, "loss": 0.3818, "step": 7850 }, { "epoch": 1.9321533923303835, "grad_norm": 2.6508660316467285, "learning_rate": 1.0678466076696165e-05, "loss": 0.3466, "step": 7860 }, { "epoch": 1.9346116027531957, "grad_norm": 11.532763481140137, "learning_rate": 1.0653883972468044e-05, "loss": 0.3598, "step": 7870 }, { "epoch": 1.937069813176008, "grad_norm": 7.340936183929443, "learning_rate": 1.0629301868239923e-05, "loss": 0.3854, "step": 7880 }, { "epoch": 1.93952802359882, "grad_norm": 14.043414115905762, "learning_rate": 1.06047197640118e-05, "loss": 0.5317, "step": 7890 }, { "epoch": 1.9419862340216323, "grad_norm": 10.200027465820312, "learning_rate": 1.0580137659783678e-05, "loss": 0.3129, "step": 7900 }, { "epoch": 1.9444444444444444, "grad_norm": 10.55239486694336, "learning_rate": 1.0555555555555555e-05, "loss": 0.4257, "step": 7910 }, { "epoch": 1.9469026548672566, "grad_norm": 7.337744235992432, "learning_rate": 1.0530973451327434e-05, "loss": 0.2876, "step": 7920 }, { "epoch": 1.949360865290069, "grad_norm": 12.484865188598633, "learning_rate": 1.0506391347099313e-05, "loss": 0.3514, "step": 7930 }, { "epoch": 1.951819075712881, "grad_norm": 8.594677925109863, "learning_rate": 1.048180924287119e-05, "loss": 0.3924, "step": 7940 }, { "epoch": 1.9542772861356932, "grad_norm": 9.535394668579102, "learning_rate": 1.0457227138643069e-05, "loss": 0.3564, "step": 7950 }, { "epoch": 1.9567354965585055, "grad_norm": 5.17072057723999, "learning_rate": 1.0432645034414946e-05, "loss": 0.3774, "step": 7960 }, { "epoch": 1.9591937069813175, "grad_norm": 7.1315155029296875, "learning_rate": 1.0408062930186824e-05, "loss": 0.4253, "step": 7970 }, { "epoch": 1.9616519174041298, "grad_norm": 11.730101585388184, "learning_rate": 1.0383480825958703e-05, "loss": 0.4306, "step": 7980 }, { "epoch": 1.964110127826942, "grad_norm": 8.80650806427002, "learning_rate": 1.035889872173058e-05, "loss": 0.3306, "step": 7990 }, { "epoch": 1.966568338249754, "grad_norm": 9.449495315551758, "learning_rate": 1.0334316617502459e-05, "loss": 0.3673, "step": 8000 }, { "epoch": 1.9690265486725664, "grad_norm": 7.2246246337890625, "learning_rate": 1.0309734513274338e-05, "loss": 0.3276, "step": 8010 }, { "epoch": 1.9714847590953786, "grad_norm": 5.302980422973633, "learning_rate": 1.0285152409046215e-05, "loss": 0.2862, "step": 8020 }, { "epoch": 1.9739429695181907, "grad_norm": 4.266974925994873, "learning_rate": 1.0260570304818094e-05, "loss": 0.2965, "step": 8030 }, { "epoch": 1.976401179941003, "grad_norm": 3.3127663135528564, "learning_rate": 1.023598820058997e-05, "loss": 0.4383, "step": 8040 }, { "epoch": 1.9788593903638152, "grad_norm": 14.069336891174316, "learning_rate": 1.021140609636185e-05, "loss": 0.2727, "step": 8050 }, { "epoch": 1.9813176007866273, "grad_norm": 3.666900873184204, "learning_rate": 1.0186823992133728e-05, "loss": 0.3545, "step": 8060 }, { "epoch": 1.9837758112094397, "grad_norm": 4.170241832733154, "learning_rate": 1.0162241887905605e-05, "loss": 0.3462, "step": 8070 }, { "epoch": 1.9862340216322516, "grad_norm": 7.18449068069458, "learning_rate": 1.0137659783677484e-05, "loss": 0.2198, "step": 8080 }, { "epoch": 1.988692232055064, "grad_norm": 2.82853364944458, "learning_rate": 1.0113077679449361e-05, "loss": 0.473, "step": 8090 }, { "epoch": 1.991150442477876, "grad_norm": 7.859971523284912, "learning_rate": 1.008849557522124e-05, "loss": 0.3582, "step": 8100 }, { "epoch": 1.9936086529006882, "grad_norm": 14.19888687133789, "learning_rate": 1.0063913470993118e-05, "loss": 0.4426, "step": 8110 }, { "epoch": 1.9960668633235006, "grad_norm": 23.176237106323242, "learning_rate": 1.0039331366764996e-05, "loss": 0.5095, "step": 8120 }, { "epoch": 1.9985250737463127, "grad_norm": 6.689763069152832, "learning_rate": 1.0014749262536874e-05, "loss": 0.3813, "step": 8130 }, { "epoch": 2.0, "eval_accuracy": 0.8466325542801826, "eval_f1_score": 0.846623080109256, "eval_loss": 0.4361102879047394, "eval_runtime": 115.6538, "eval_samples_per_second": 62.523, "eval_steps_per_second": 3.908, "step": 8136 }, { "epoch": 2.000983284169125, "grad_norm": 9.908890724182129, "learning_rate": 9.990167158308753e-06, "loss": 0.4353, "step": 8140 }, { "epoch": 2.003441494591937, "grad_norm": 14.876886367797852, "learning_rate": 9.96558505408063e-06, "loss": 0.3876, "step": 8150 }, { "epoch": 2.005899705014749, "grad_norm": 6.554903030395508, "learning_rate": 9.941002949852507e-06, "loss": 0.2561, "step": 8160 }, { "epoch": 2.0083579154375615, "grad_norm": 8.475651741027832, "learning_rate": 9.916420845624384e-06, "loss": 0.3494, "step": 8170 }, { "epoch": 2.010816125860374, "grad_norm": 5.022943496704102, "learning_rate": 9.891838741396263e-06, "loss": 0.3518, "step": 8180 }, { "epoch": 2.0132743362831858, "grad_norm": 11.575230598449707, "learning_rate": 9.867256637168142e-06, "loss": 0.3272, "step": 8190 }, { "epoch": 2.015732546705998, "grad_norm": 16.65123748779297, "learning_rate": 9.842674532940019e-06, "loss": 0.3621, "step": 8200 }, { "epoch": 2.01819075712881, "grad_norm": 3.8791913986206055, "learning_rate": 9.818092428711897e-06, "loss": 0.3048, "step": 8210 }, { "epoch": 2.0206489675516224, "grad_norm": 15.01823616027832, "learning_rate": 9.793510324483776e-06, "loss": 0.322, "step": 8220 }, { "epoch": 2.0231071779744347, "grad_norm": 21.705373764038086, "learning_rate": 9.768928220255653e-06, "loss": 0.3449, "step": 8230 }, { "epoch": 2.0255653883972466, "grad_norm": 10.538731575012207, "learning_rate": 9.744346116027532e-06, "loss": 0.3853, "step": 8240 }, { "epoch": 2.028023598820059, "grad_norm": 10.336060523986816, "learning_rate": 9.719764011799409e-06, "loss": 0.3322, "step": 8250 }, { "epoch": 2.0304818092428714, "grad_norm": 6.867379188537598, "learning_rate": 9.695181907571288e-06, "loss": 0.2795, "step": 8260 }, { "epoch": 2.0329400196656833, "grad_norm": 10.50891399383545, "learning_rate": 9.670599803343167e-06, "loss": 0.4155, "step": 8270 }, { "epoch": 2.0353982300884956, "grad_norm": 9.830208778381348, "learning_rate": 9.646017699115044e-06, "loss": 0.4071, "step": 8280 }, { "epoch": 2.037856440511308, "grad_norm": 6.981502532958984, "learning_rate": 9.621435594886922e-06, "loss": 0.2783, "step": 8290 }, { "epoch": 2.04031465093412, "grad_norm": 1.2106738090515137, "learning_rate": 9.5968534906588e-06, "loss": 0.2901, "step": 8300 }, { "epoch": 2.0427728613569323, "grad_norm": 4.568361759185791, "learning_rate": 9.572271386430678e-06, "loss": 0.2913, "step": 8310 }, { "epoch": 2.045231071779744, "grad_norm": 6.309854507446289, "learning_rate": 9.547689282202557e-06, "loss": 0.2945, "step": 8320 }, { "epoch": 2.0476892822025565, "grad_norm": 2.5507636070251465, "learning_rate": 9.523107177974434e-06, "loss": 0.2763, "step": 8330 }, { "epoch": 2.050147492625369, "grad_norm": 7.41677188873291, "learning_rate": 9.498525073746313e-06, "loss": 0.3985, "step": 8340 }, { "epoch": 2.052605703048181, "grad_norm": 7.712475776672363, "learning_rate": 9.473942969518191e-06, "loss": 0.2395, "step": 8350 }, { "epoch": 2.055063913470993, "grad_norm": 22.012096405029297, "learning_rate": 9.449360865290068e-06, "loss": 0.2821, "step": 8360 }, { "epoch": 2.0575221238938055, "grad_norm": 13.786518096923828, "learning_rate": 9.424778761061947e-06, "loss": 0.3222, "step": 8370 }, { "epoch": 2.0599803343166174, "grad_norm": 6.532347202301025, "learning_rate": 9.400196656833824e-06, "loss": 0.3184, "step": 8380 }, { "epoch": 2.06243854473943, "grad_norm": 9.56808853149414, "learning_rate": 9.375614552605703e-06, "loss": 0.1889, "step": 8390 }, { "epoch": 2.0648967551622417, "grad_norm": 4.872052192687988, "learning_rate": 9.351032448377582e-06, "loss": 0.3091, "step": 8400 }, { "epoch": 2.067354965585054, "grad_norm": 15.540621757507324, "learning_rate": 9.326450344149459e-06, "loss": 0.4768, "step": 8410 }, { "epoch": 2.0698131760078664, "grad_norm": 35.72615432739258, "learning_rate": 9.301868239921338e-06, "loss": 0.302, "step": 8420 }, { "epoch": 2.0722713864306783, "grad_norm": 9.76016616821289, "learning_rate": 9.277286135693215e-06, "loss": 0.3336, "step": 8430 }, { "epoch": 2.0747295968534907, "grad_norm": 5.8219428062438965, "learning_rate": 9.252704031465093e-06, "loss": 0.3298, "step": 8440 }, { "epoch": 2.077187807276303, "grad_norm": 11.746243476867676, "learning_rate": 9.228121927236972e-06, "loss": 0.3501, "step": 8450 }, { "epoch": 2.079646017699115, "grad_norm": 4.718607425689697, "learning_rate": 9.20353982300885e-06, "loss": 0.2832, "step": 8460 }, { "epoch": 2.0821042281219273, "grad_norm": 21.068126678466797, "learning_rate": 9.178957718780728e-06, "loss": 0.2702, "step": 8470 }, { "epoch": 2.084562438544739, "grad_norm": 12.166190147399902, "learning_rate": 9.154375614552607e-06, "loss": 0.3927, "step": 8480 }, { "epoch": 2.0870206489675516, "grad_norm": 9.270221710205078, "learning_rate": 9.129793510324484e-06, "loss": 0.2255, "step": 8490 }, { "epoch": 2.089478859390364, "grad_norm": 9.661781311035156, "learning_rate": 9.105211406096362e-06, "loss": 0.4007, "step": 8500 }, { "epoch": 2.091937069813176, "grad_norm": 8.361656188964844, "learning_rate": 9.08062930186824e-06, "loss": 0.4228, "step": 8510 }, { "epoch": 2.094395280235988, "grad_norm": 9.960454940795898, "learning_rate": 9.056047197640118e-06, "loss": 0.3529, "step": 8520 }, { "epoch": 2.0968534906588006, "grad_norm": 5.192384719848633, "learning_rate": 9.031465093411997e-06, "loss": 0.2654, "step": 8530 }, { "epoch": 2.0993117010816125, "grad_norm": 7.039541244506836, "learning_rate": 9.006882989183874e-06, "loss": 0.1912, "step": 8540 }, { "epoch": 2.101769911504425, "grad_norm": 2.680172920227051, "learning_rate": 8.982300884955753e-06, "loss": 0.3084, "step": 8550 }, { "epoch": 2.104228121927237, "grad_norm": 8.640162467956543, "learning_rate": 8.95771878072763e-06, "loss": 0.3496, "step": 8560 }, { "epoch": 2.106686332350049, "grad_norm": 4.36017370223999, "learning_rate": 8.933136676499509e-06, "loss": 0.2251, "step": 8570 }, { "epoch": 2.1091445427728615, "grad_norm": 13.276532173156738, "learning_rate": 8.908554572271387e-06, "loss": 0.3938, "step": 8580 }, { "epoch": 2.1116027531956734, "grad_norm": 21.639984130859375, "learning_rate": 8.883972468043264e-06, "loss": 0.2898, "step": 8590 }, { "epoch": 2.1140609636184857, "grad_norm": 20.6730899810791, "learning_rate": 8.859390363815143e-06, "loss": 0.29, "step": 8600 }, { "epoch": 2.116519174041298, "grad_norm": 10.23141098022461, "learning_rate": 8.834808259587022e-06, "loss": 0.3209, "step": 8610 }, { "epoch": 2.11897738446411, "grad_norm": 11.03176212310791, "learning_rate": 8.810226155358899e-06, "loss": 0.3678, "step": 8620 }, { "epoch": 2.1214355948869223, "grad_norm": 11.617761611938477, "learning_rate": 8.785644051130778e-06, "loss": 0.3545, "step": 8630 }, { "epoch": 2.1238938053097347, "grad_norm": 23.402400970458984, "learning_rate": 8.761061946902655e-06, "loss": 0.2815, "step": 8640 }, { "epoch": 2.1263520157325466, "grad_norm": 12.469143867492676, "learning_rate": 8.736479842674533e-06, "loss": 0.3441, "step": 8650 }, { "epoch": 2.128810226155359, "grad_norm": 12.431056022644043, "learning_rate": 8.711897738446412e-06, "loss": 0.2377, "step": 8660 }, { "epoch": 2.131268436578171, "grad_norm": 8.038508415222168, "learning_rate": 8.68731563421829e-06, "loss": 0.3266, "step": 8670 }, { "epoch": 2.1337266470009832, "grad_norm": 6.502164840698242, "learning_rate": 8.662733529990168e-06, "loss": 0.4064, "step": 8680 }, { "epoch": 2.1361848574237956, "grad_norm": 18.96112632751465, "learning_rate": 8.638151425762045e-06, "loss": 0.3586, "step": 8690 }, { "epoch": 2.1386430678466075, "grad_norm": 9.480737686157227, "learning_rate": 8.613569321533924e-06, "loss": 0.3175, "step": 8700 }, { "epoch": 2.14110127826942, "grad_norm": 9.9135103225708, "learning_rate": 8.588987217305803e-06, "loss": 0.3781, "step": 8710 }, { "epoch": 2.1435594886922322, "grad_norm": 17.052776336669922, "learning_rate": 8.56440511307768e-06, "loss": 0.3202, "step": 8720 }, { "epoch": 2.146017699115044, "grad_norm": 7.652860164642334, "learning_rate": 8.539823008849558e-06, "loss": 0.3006, "step": 8730 }, { "epoch": 2.1484759095378565, "grad_norm": 10.335585594177246, "learning_rate": 8.515240904621437e-06, "loss": 0.3503, "step": 8740 }, { "epoch": 2.1509341199606684, "grad_norm": 18.565309524536133, "learning_rate": 8.490658800393314e-06, "loss": 0.4268, "step": 8750 }, { "epoch": 2.1533923303834808, "grad_norm": 7.606307029724121, "learning_rate": 8.466076696165193e-06, "loss": 0.3051, "step": 8760 }, { "epoch": 2.155850540806293, "grad_norm": 3.8772904872894287, "learning_rate": 8.44149459193707e-06, "loss": 0.2578, "step": 8770 }, { "epoch": 2.158308751229105, "grad_norm": 11.16654109954834, "learning_rate": 8.416912487708949e-06, "loss": 0.1985, "step": 8780 }, { "epoch": 2.1607669616519174, "grad_norm": 12.004631042480469, "learning_rate": 8.392330383480827e-06, "loss": 0.3665, "step": 8790 }, { "epoch": 2.1632251720747298, "grad_norm": 15.196014404296875, "learning_rate": 8.367748279252705e-06, "loss": 0.308, "step": 8800 }, { "epoch": 2.1656833824975417, "grad_norm": 20.291990280151367, "learning_rate": 8.343166175024583e-06, "loss": 0.3646, "step": 8810 }, { "epoch": 2.168141592920354, "grad_norm": 4.644341945648193, "learning_rate": 8.31858407079646e-06, "loss": 0.316, "step": 8820 }, { "epoch": 2.1705998033431664, "grad_norm": 8.904132843017578, "learning_rate": 8.294001966568339e-06, "loss": 0.3231, "step": 8830 }, { "epoch": 2.1730580137659783, "grad_norm": 7.5388875007629395, "learning_rate": 8.269419862340218e-06, "loss": 0.3289, "step": 8840 }, { "epoch": 2.1755162241887906, "grad_norm": 14.04014778137207, "learning_rate": 8.244837758112095e-06, "loss": 0.279, "step": 8850 }, { "epoch": 2.1779744346116026, "grad_norm": 11.26218318939209, "learning_rate": 8.220255653883974e-06, "loss": 0.3759, "step": 8860 }, { "epoch": 2.180432645034415, "grad_norm": 3.836040496826172, "learning_rate": 8.19567354965585e-06, "loss": 0.1992, "step": 8870 }, { "epoch": 2.1828908554572273, "grad_norm": 18.005512237548828, "learning_rate": 8.171091445427728e-06, "loss": 0.4554, "step": 8880 }, { "epoch": 2.185349065880039, "grad_norm": 10.465679168701172, "learning_rate": 8.146509341199606e-06, "loss": 0.2892, "step": 8890 }, { "epoch": 2.1878072763028515, "grad_norm": 10.541736602783203, "learning_rate": 8.121927236971483e-06, "loss": 0.3465, "step": 8900 }, { "epoch": 2.190265486725664, "grad_norm": 7.0997314453125, "learning_rate": 8.097345132743362e-06, "loss": 0.3436, "step": 8910 }, { "epoch": 2.192723697148476, "grad_norm": 2.7644195556640625, "learning_rate": 8.072763028515241e-06, "loss": 0.236, "step": 8920 }, { "epoch": 2.195181907571288, "grad_norm": 17.0452823638916, "learning_rate": 8.048180924287118e-06, "loss": 0.3388, "step": 8930 }, { "epoch": 2.1976401179941005, "grad_norm": 18.198911666870117, "learning_rate": 8.023598820058997e-06, "loss": 0.4071, "step": 8940 }, { "epoch": 2.2000983284169124, "grad_norm": 9.081130981445312, "learning_rate": 7.999016715830874e-06, "loss": 0.2361, "step": 8950 }, { "epoch": 2.202556538839725, "grad_norm": 6.3903422355651855, "learning_rate": 7.974434611602753e-06, "loss": 0.2797, "step": 8960 }, { "epoch": 2.2050147492625367, "grad_norm": 6.799188613891602, "learning_rate": 7.949852507374631e-06, "loss": 0.221, "step": 8970 }, { "epoch": 2.207472959685349, "grad_norm": 9.023968696594238, "learning_rate": 7.925270403146508e-06, "loss": 0.4334, "step": 8980 }, { "epoch": 2.2099311701081614, "grad_norm": 2.599860668182373, "learning_rate": 7.900688298918387e-06, "loss": 0.263, "step": 8990 }, { "epoch": 2.2123893805309733, "grad_norm": 17.64944839477539, "learning_rate": 7.876106194690266e-06, "loss": 0.3134, "step": 9000 }, { "epoch": 2.2148475909537857, "grad_norm": 4.804849624633789, "learning_rate": 7.851524090462143e-06, "loss": 0.2835, "step": 9010 }, { "epoch": 2.2173058013765976, "grad_norm": 16.374195098876953, "learning_rate": 7.826941986234022e-06, "loss": 0.3113, "step": 9020 }, { "epoch": 2.21976401179941, "grad_norm": 8.041377067565918, "learning_rate": 7.802359882005899e-06, "loss": 0.451, "step": 9030 }, { "epoch": 2.2222222222222223, "grad_norm": 3.897434711456299, "learning_rate": 7.777777777777777e-06, "loss": 0.1907, "step": 9040 }, { "epoch": 2.2246804326450342, "grad_norm": 6.618371963500977, "learning_rate": 7.753195673549656e-06, "loss": 0.3625, "step": 9050 }, { "epoch": 2.2271386430678466, "grad_norm": 12.240897178649902, "learning_rate": 7.728613569321533e-06, "loss": 0.2627, "step": 9060 }, { "epoch": 2.229596853490659, "grad_norm": 5.981658458709717, "learning_rate": 7.704031465093412e-06, "loss": 0.2647, "step": 9070 }, { "epoch": 2.232055063913471, "grad_norm": 19.141422271728516, "learning_rate": 7.67944936086529e-06, "loss": 0.3152, "step": 9080 }, { "epoch": 2.234513274336283, "grad_norm": 5.902695655822754, "learning_rate": 7.654867256637168e-06, "loss": 0.4195, "step": 9090 }, { "epoch": 2.2369714847590956, "grad_norm": 13.614252090454102, "learning_rate": 7.630285152409047e-06, "loss": 0.3851, "step": 9100 }, { "epoch": 2.2394296951819075, "grad_norm": 12.172417640686035, "learning_rate": 7.6057030481809245e-06, "loss": 0.257, "step": 9110 }, { "epoch": 2.24188790560472, "grad_norm": 8.540313720703125, "learning_rate": 7.581120943952802e-06, "loss": 0.2703, "step": 9120 }, { "epoch": 2.2443461160275318, "grad_norm": 18.16095733642578, "learning_rate": 7.55653883972468e-06, "loss": 0.2412, "step": 9130 }, { "epoch": 2.246804326450344, "grad_norm": 8.029040336608887, "learning_rate": 7.531956735496558e-06, "loss": 0.366, "step": 9140 }, { "epoch": 2.2492625368731565, "grad_norm": 6.533568859100342, "learning_rate": 7.507374631268437e-06, "loss": 0.2283, "step": 9150 }, { "epoch": 2.2517207472959684, "grad_norm": 3.655179977416992, "learning_rate": 7.482792527040315e-06, "loss": 0.3352, "step": 9160 }, { "epoch": 2.2541789577187807, "grad_norm": 3.687194347381592, "learning_rate": 7.458210422812193e-06, "loss": 0.3295, "step": 9170 }, { "epoch": 2.256637168141593, "grad_norm": 6.481263160705566, "learning_rate": 7.433628318584071e-06, "loss": 0.1906, "step": 9180 }, { "epoch": 2.259095378564405, "grad_norm": 11.8029203414917, "learning_rate": 7.409046214355949e-06, "loss": 0.4138, "step": 9190 }, { "epoch": 2.2615535889872174, "grad_norm": 14.081475257873535, "learning_rate": 7.384464110127827e-06, "loss": 0.405, "step": 9200 }, { "epoch": 2.2640117994100297, "grad_norm": 2.4396369457244873, "learning_rate": 7.359882005899705e-06, "loss": 0.2371, "step": 9210 }, { "epoch": 2.2664700098328416, "grad_norm": 5.568498611450195, "learning_rate": 7.335299901671583e-06, "loss": 0.2813, "step": 9220 }, { "epoch": 2.268928220255654, "grad_norm": 16.45796775817871, "learning_rate": 7.310717797443461e-06, "loss": 0.3574, "step": 9230 }, { "epoch": 2.271386430678466, "grad_norm": 18.030031204223633, "learning_rate": 7.28613569321534e-06, "loss": 0.3539, "step": 9240 }, { "epoch": 2.2738446411012783, "grad_norm": 7.639561176300049, "learning_rate": 7.261553588987218e-06, "loss": 0.2198, "step": 9250 }, { "epoch": 2.2763028515240906, "grad_norm": 10.888632774353027, "learning_rate": 7.2369714847590955e-06, "loss": 0.2598, "step": 9260 }, { "epoch": 2.2787610619469025, "grad_norm": 16.70732879638672, "learning_rate": 7.212389380530973e-06, "loss": 0.2931, "step": 9270 }, { "epoch": 2.281219272369715, "grad_norm": 7.887454032897949, "learning_rate": 7.187807276302852e-06, "loss": 0.25, "step": 9280 }, { "epoch": 2.283677482792527, "grad_norm": 18.320510864257812, "learning_rate": 7.16322517207473e-06, "loss": 0.1957, "step": 9290 }, { "epoch": 2.286135693215339, "grad_norm": 12.72488784790039, "learning_rate": 7.138643067846608e-06, "loss": 0.2541, "step": 9300 }, { "epoch": 2.2885939036381515, "grad_norm": 10.377412796020508, "learning_rate": 7.114060963618486e-06, "loss": 0.398, "step": 9310 }, { "epoch": 2.2910521140609634, "grad_norm": 16.008506774902344, "learning_rate": 7.089478859390365e-06, "loss": 0.4152, "step": 9320 }, { "epoch": 2.293510324483776, "grad_norm": 16.49017333984375, "learning_rate": 7.0648967551622425e-06, "loss": 0.3382, "step": 9330 }, { "epoch": 2.295968534906588, "grad_norm": 9.706487655639648, "learning_rate": 7.04031465093412e-06, "loss": 0.2775, "step": 9340 }, { "epoch": 2.2984267453294, "grad_norm": 8.533392906188965, "learning_rate": 7.015732546705998e-06, "loss": 0.3087, "step": 9350 }, { "epoch": 2.3008849557522124, "grad_norm": 18.98924446105957, "learning_rate": 6.991150442477877e-06, "loss": 0.3388, "step": 9360 }, { "epoch": 2.3033431661750248, "grad_norm": 14.038328170776367, "learning_rate": 6.966568338249755e-06, "loss": 0.3865, "step": 9370 }, { "epoch": 2.3058013765978367, "grad_norm": 5.217092514038086, "learning_rate": 6.941986234021633e-06, "loss": 0.3565, "step": 9380 }, { "epoch": 2.308259587020649, "grad_norm": 9.518186569213867, "learning_rate": 6.917404129793511e-06, "loss": 0.2304, "step": 9390 }, { "epoch": 2.310717797443461, "grad_norm": 21.665977478027344, "learning_rate": 6.892822025565389e-06, "loss": 0.3893, "step": 9400 }, { "epoch": 2.3131760078662733, "grad_norm": 5.909334182739258, "learning_rate": 6.8682399213372665e-06, "loss": 0.2755, "step": 9410 }, { "epoch": 2.3156342182890857, "grad_norm": 12.893810272216797, "learning_rate": 6.843657817109144e-06, "loss": 0.359, "step": 9420 }, { "epoch": 2.3180924287118976, "grad_norm": 11.858681678771973, "learning_rate": 6.819075712881022e-06, "loss": 0.3544, "step": 9430 }, { "epoch": 2.32055063913471, "grad_norm": 7.654836654663086, "learning_rate": 6.7944936086529e-06, "loss": 0.2312, "step": 9440 }, { "epoch": 2.3230088495575223, "grad_norm": 15.187524795532227, "learning_rate": 6.769911504424779e-06, "loss": 0.2816, "step": 9450 }, { "epoch": 2.325467059980334, "grad_norm": 3.723843812942505, "learning_rate": 6.745329400196657e-06, "loss": 0.2472, "step": 9460 }, { "epoch": 2.3279252704031466, "grad_norm": 5.043320655822754, "learning_rate": 6.720747295968535e-06, "loss": 0.4022, "step": 9470 }, { "epoch": 2.330383480825959, "grad_norm": 8.142643928527832, "learning_rate": 6.696165191740413e-06, "loss": 0.4104, "step": 9480 }, { "epoch": 2.332841691248771, "grad_norm": 9.051960945129395, "learning_rate": 6.671583087512291e-06, "loss": 0.2809, "step": 9490 }, { "epoch": 2.335299901671583, "grad_norm": 4.340271472930908, "learning_rate": 6.647000983284169e-06, "loss": 0.196, "step": 9500 }, { "epoch": 2.337758112094395, "grad_norm": 4.408080101013184, "learning_rate": 6.622418879056047e-06, "loss": 0.2671, "step": 9510 }, { "epoch": 2.3402163225172075, "grad_norm": 11.761630058288574, "learning_rate": 6.597836774827925e-06, "loss": 0.2504, "step": 9520 }, { "epoch": 2.34267453294002, "grad_norm": 14.959927558898926, "learning_rate": 6.573254670599803e-06, "loss": 0.2385, "step": 9530 }, { "epoch": 2.3451327433628317, "grad_norm": 15.52859878540039, "learning_rate": 6.548672566371682e-06, "loss": 0.2748, "step": 9540 }, { "epoch": 2.347590953785644, "grad_norm": 4.462477684020996, "learning_rate": 6.52409046214356e-06, "loss": 0.3156, "step": 9550 }, { "epoch": 2.350049164208456, "grad_norm": 8.269617080688477, "learning_rate": 6.4995083579154375e-06, "loss": 0.3142, "step": 9560 }, { "epoch": 2.3525073746312684, "grad_norm": 5.55247163772583, "learning_rate": 6.4749262536873154e-06, "loss": 0.4078, "step": 9570 }, { "epoch": 2.3549655850540807, "grad_norm": 12.719615936279297, "learning_rate": 6.450344149459194e-06, "loss": 0.3175, "step": 9580 }, { "epoch": 2.357423795476893, "grad_norm": 12.019001007080078, "learning_rate": 6.425762045231072e-06, "loss": 0.2423, "step": 9590 }, { "epoch": 2.359882005899705, "grad_norm": 16.06062889099121, "learning_rate": 6.40117994100295e-06, "loss": 0.3617, "step": 9600 }, { "epoch": 2.3623402163225173, "grad_norm": 7.1149492263793945, "learning_rate": 6.376597836774828e-06, "loss": 0.3484, "step": 9610 }, { "epoch": 2.3647984267453293, "grad_norm": 9.321300506591797, "learning_rate": 6.352015732546707e-06, "loss": 0.1991, "step": 9620 }, { "epoch": 2.3672566371681416, "grad_norm": 11.042052268981934, "learning_rate": 6.3274336283185845e-06, "loss": 0.3095, "step": 9630 }, { "epoch": 2.369714847590954, "grad_norm": 9.002201080322266, "learning_rate": 6.3028515240904624e-06, "loss": 0.3742, "step": 9640 }, { "epoch": 2.372173058013766, "grad_norm": 8.054828643798828, "learning_rate": 6.27826941986234e-06, "loss": 0.3603, "step": 9650 }, { "epoch": 2.3746312684365782, "grad_norm": 12.028568267822266, "learning_rate": 6.253687315634218e-06, "loss": 0.3293, "step": 9660 }, { "epoch": 2.37708947885939, "grad_norm": 20.15642738342285, "learning_rate": 6.229105211406097e-06, "loss": 0.3878, "step": 9670 }, { "epoch": 2.3795476892822025, "grad_norm": 8.768622398376465, "learning_rate": 6.204523107177975e-06, "loss": 0.32, "step": 9680 }, { "epoch": 2.382005899705015, "grad_norm": 8.151020050048828, "learning_rate": 6.179941002949853e-06, "loss": 0.2621, "step": 9690 }, { "epoch": 2.3844641101278268, "grad_norm": 3.683985710144043, "learning_rate": 6.155358898721731e-06, "loss": 0.2883, "step": 9700 }, { "epoch": 2.386922320550639, "grad_norm": 4.283771514892578, "learning_rate": 6.130776794493609e-06, "loss": 0.1778, "step": 9710 }, { "epoch": 2.3893805309734515, "grad_norm": 6.5790510177612305, "learning_rate": 6.106194690265487e-06, "loss": 0.3931, "step": 9720 }, { "epoch": 2.3918387413962634, "grad_norm": 5.95913553237915, "learning_rate": 6.081612586037365e-06, "loss": 0.2291, "step": 9730 }, { "epoch": 2.3942969518190758, "grad_norm": 7.437248229980469, "learning_rate": 6.057030481809243e-06, "loss": 0.2923, "step": 9740 }, { "epoch": 2.396755162241888, "grad_norm": 7.674708843231201, "learning_rate": 6.032448377581122e-06, "loss": 0.1762, "step": 9750 }, { "epoch": 2.3992133726647, "grad_norm": 9.4530668258667, "learning_rate": 6.007866273352999e-06, "loss": 0.331, "step": 9760 }, { "epoch": 2.4016715830875124, "grad_norm": 3.1820263862609863, "learning_rate": 5.983284169124877e-06, "loss": 0.3715, "step": 9770 }, { "epoch": 2.4041297935103243, "grad_norm": 7.522729873657227, "learning_rate": 5.958702064896755e-06, "loss": 0.3661, "step": 9780 }, { "epoch": 2.4065880039331367, "grad_norm": 14.527021408081055, "learning_rate": 5.9341199606686335e-06, "loss": 0.3453, "step": 9790 }, { "epoch": 2.409046214355949, "grad_norm": 7.238635063171387, "learning_rate": 5.909537856440511e-06, "loss": 0.2616, "step": 9800 }, { "epoch": 2.411504424778761, "grad_norm": 15.283666610717773, "learning_rate": 5.884955752212389e-06, "loss": 0.2273, "step": 9810 }, { "epoch": 2.4139626352015733, "grad_norm": 6.533797740936279, "learning_rate": 5.860373647984267e-06, "loss": 0.3078, "step": 9820 }, { "epoch": 2.4164208456243856, "grad_norm": 13.70199203491211, "learning_rate": 5.835791543756145e-06, "loss": 0.3211, "step": 9830 }, { "epoch": 2.4188790560471976, "grad_norm": 27.613529205322266, "learning_rate": 5.811209439528024e-06, "loss": 0.4125, "step": 9840 }, { "epoch": 2.42133726647001, "grad_norm": 7.088224411010742, "learning_rate": 5.786627335299902e-06, "loss": 0.2788, "step": 9850 }, { "epoch": 2.4237954768928223, "grad_norm": 7.596344470977783, "learning_rate": 5.76204523107178e-06, "loss": 0.2758, "step": 9860 }, { "epoch": 2.426253687315634, "grad_norm": 7.947212219238281, "learning_rate": 5.7374631268436575e-06, "loss": 0.2056, "step": 9870 }, { "epoch": 2.4287118977384465, "grad_norm": 10.88403034210205, "learning_rate": 5.712881022615536e-06, "loss": 0.3736, "step": 9880 }, { "epoch": 2.4311701081612584, "grad_norm": 6.6369099617004395, "learning_rate": 5.688298918387414e-06, "loss": 0.4953, "step": 9890 }, { "epoch": 2.433628318584071, "grad_norm": 9.863775253295898, "learning_rate": 5.663716814159292e-06, "loss": 0.3007, "step": 9900 }, { "epoch": 2.436086529006883, "grad_norm": 10.992876052856445, "learning_rate": 5.63913470993117e-06, "loss": 0.4232, "step": 9910 }, { "epoch": 2.438544739429695, "grad_norm": 12.56666088104248, "learning_rate": 5.614552605703049e-06, "loss": 0.3959, "step": 9920 }, { "epoch": 2.4410029498525074, "grad_norm": 6.205108165740967, "learning_rate": 5.589970501474927e-06, "loss": 0.3918, "step": 9930 }, { "epoch": 2.4434611602753193, "grad_norm": 7.235611915588379, "learning_rate": 5.5653883972468045e-06, "loss": 0.265, "step": 9940 }, { "epoch": 2.4459193706981317, "grad_norm": 17.367456436157227, "learning_rate": 5.540806293018682e-06, "loss": 0.2521, "step": 9950 }, { "epoch": 2.448377581120944, "grad_norm": 23.38491439819336, "learning_rate": 5.51622418879056e-06, "loss": 0.3613, "step": 9960 }, { "epoch": 2.450835791543756, "grad_norm": 14.698434829711914, "learning_rate": 5.491642084562439e-06, "loss": 0.407, "step": 9970 }, { "epoch": 2.4532940019665683, "grad_norm": 2.6294500827789307, "learning_rate": 5.467059980334317e-06, "loss": 0.2159, "step": 9980 }, { "epoch": 2.4557522123893807, "grad_norm": 8.413351058959961, "learning_rate": 5.442477876106195e-06, "loss": 0.3215, "step": 9990 }, { "epoch": 2.4582104228121926, "grad_norm": 9.7800874710083, "learning_rate": 5.417895771878073e-06, "loss": 0.2391, "step": 10000 }, { "epoch": 2.460668633235005, "grad_norm": 19.572553634643555, "learning_rate": 5.3933136676499515e-06, "loss": 0.3881, "step": 10010 }, { "epoch": 2.4631268436578173, "grad_norm": 5.454105377197266, "learning_rate": 5.368731563421829e-06, "loss": 0.2649, "step": 10020 }, { "epoch": 2.4655850540806292, "grad_norm": 22.332155227661133, "learning_rate": 5.344149459193707e-06, "loss": 0.3732, "step": 10030 }, { "epoch": 2.4680432645034416, "grad_norm": 11.184699058532715, "learning_rate": 5.319567354965585e-06, "loss": 0.3309, "step": 10040 }, { "epoch": 2.4705014749262535, "grad_norm": 6.5970611572265625, "learning_rate": 5.294985250737464e-06, "loss": 0.3061, "step": 10050 }, { "epoch": 2.472959685349066, "grad_norm": 4.473758220672607, "learning_rate": 5.270403146509342e-06, "loss": 0.3422, "step": 10060 }, { "epoch": 2.475417895771878, "grad_norm": 9.303690910339355, "learning_rate": 5.24582104228122e-06, "loss": 0.2593, "step": 10070 }, { "epoch": 2.47787610619469, "grad_norm": 0.7857942581176758, "learning_rate": 5.221238938053098e-06, "loss": 0.2471, "step": 10080 }, { "epoch": 2.4803343166175025, "grad_norm": 12.391585350036621, "learning_rate": 5.1966568338249755e-06, "loss": 0.2962, "step": 10090 }, { "epoch": 2.482792527040315, "grad_norm": 24.552661895751953, "learning_rate": 5.172074729596854e-06, "loss": 0.3019, "step": 10100 }, { "epoch": 2.4852507374631267, "grad_norm": 10.578263282775879, "learning_rate": 5.147492625368732e-06, "loss": 0.3858, "step": 10110 }, { "epoch": 2.487708947885939, "grad_norm": 31.030359268188477, "learning_rate": 5.122910521140609e-06, "loss": 0.3074, "step": 10120 }, { "epoch": 2.4901671583087515, "grad_norm": 11.698269844055176, "learning_rate": 5.098328416912487e-06, "loss": 0.3324, "step": 10130 }, { "epoch": 2.4926253687315634, "grad_norm": 5.473494052886963, "learning_rate": 5.073746312684366e-06, "loss": 0.383, "step": 10140 }, { "epoch": 2.4950835791543757, "grad_norm": 4.614388942718506, "learning_rate": 5.049164208456244e-06, "loss": 0.2347, "step": 10150 }, { "epoch": 2.4975417895771876, "grad_norm": 14.550966262817383, "learning_rate": 5.024582104228122e-06, "loss": 0.2243, "step": 10160 }, { "epoch": 2.5, "grad_norm": 8.412307739257812, "learning_rate": 4.9999999999999996e-06, "loss": 0.3123, "step": 10170 }, { "epoch": 2.5024582104228124, "grad_norm": 14.030346870422363, "learning_rate": 4.975417895771878e-06, "loss": 0.2269, "step": 10180 }, { "epoch": 2.5049164208456243, "grad_norm": 22.687368392944336, "learning_rate": 4.950835791543756e-06, "loss": 0.2621, "step": 10190 }, { "epoch": 2.5073746312684366, "grad_norm": 2.934586763381958, "learning_rate": 4.926253687315634e-06, "loss": 0.2002, "step": 10200 }, { "epoch": 2.5098328416912485, "grad_norm": 9.886433601379395, "learning_rate": 4.901671583087512e-06, "loss": 0.3033, "step": 10210 }, { "epoch": 2.512291052114061, "grad_norm": 7.895692825317383, "learning_rate": 4.87708947885939e-06, "loss": 0.2283, "step": 10220 }, { "epoch": 2.5147492625368733, "grad_norm": 6.421346664428711, "learning_rate": 4.852507374631269e-06, "loss": 0.3525, "step": 10230 }, { "epoch": 2.5172074729596856, "grad_norm": 7.88395881652832, "learning_rate": 4.8279252704031466e-06, "loss": 0.2488, "step": 10240 }, { "epoch": 2.5196656833824975, "grad_norm": 15.55846118927002, "learning_rate": 4.8033431661750244e-06, "loss": 0.3333, "step": 10250 }, { "epoch": 2.52212389380531, "grad_norm": 23.366104125976562, "learning_rate": 4.778761061946902e-06, "loss": 0.2701, "step": 10260 }, { "epoch": 2.524582104228122, "grad_norm": 18.882081985473633, "learning_rate": 4.754178957718781e-06, "loss": 0.4275, "step": 10270 }, { "epoch": 2.527040314650934, "grad_norm": 7.167839527130127, "learning_rate": 4.729596853490659e-06, "loss": 0.2491, "step": 10280 }, { "epoch": 2.5294985250737465, "grad_norm": 13.428461074829102, "learning_rate": 4.705014749262537e-06, "loss": 0.3094, "step": 10290 }, { "epoch": 2.5319567354965584, "grad_norm": 8.71884536743164, "learning_rate": 4.680432645034415e-06, "loss": 0.3775, "step": 10300 }, { "epoch": 2.5344149459193708, "grad_norm": 19.045862197875977, "learning_rate": 4.6558505408062935e-06, "loss": 0.3393, "step": 10310 }, { "epoch": 2.5368731563421827, "grad_norm": 10.873698234558105, "learning_rate": 4.6312684365781714e-06, "loss": 0.3394, "step": 10320 }, { "epoch": 2.539331366764995, "grad_norm": 4.719176292419434, "learning_rate": 4.606686332350049e-06, "loss": 0.504, "step": 10330 }, { "epoch": 2.5417895771878074, "grad_norm": 6.712222099304199, "learning_rate": 4.582104228121927e-06, "loss": 0.2082, "step": 10340 }, { "epoch": 2.5442477876106193, "grad_norm": 15.01922607421875, "learning_rate": 4.557522123893806e-06, "loss": 0.2924, "step": 10350 }, { "epoch": 2.5467059980334317, "grad_norm": 15.639728546142578, "learning_rate": 4.532940019665684e-06, "loss": 0.2924, "step": 10360 }, { "epoch": 2.5491642084562436, "grad_norm": 13.592108726501465, "learning_rate": 4.508357915437562e-06, "loss": 0.3439, "step": 10370 }, { "epoch": 2.551622418879056, "grad_norm": 1.9944034814834595, "learning_rate": 4.48377581120944e-06, "loss": 0.329, "step": 10380 }, { "epoch": 2.5540806293018683, "grad_norm": 2.0162298679351807, "learning_rate": 4.459193706981318e-06, "loss": 0.2334, "step": 10390 }, { "epoch": 2.5565388397246807, "grad_norm": 14.217473030090332, "learning_rate": 4.434611602753196e-06, "loss": 0.3058, "step": 10400 }, { "epoch": 2.5589970501474926, "grad_norm": 13.582987785339355, "learning_rate": 4.410029498525074e-06, "loss": 0.3511, "step": 10410 }, { "epoch": 2.561455260570305, "grad_norm": 2.6844425201416016, "learning_rate": 4.385447394296952e-06, "loss": 0.2656, "step": 10420 }, { "epoch": 2.563913470993117, "grad_norm": 0.7755809426307678, "learning_rate": 4.36086529006883e-06, "loss": 0.3017, "step": 10430 }, { "epoch": 2.566371681415929, "grad_norm": 12.251648902893066, "learning_rate": 4.336283185840709e-06, "loss": 0.365, "step": 10440 }, { "epoch": 2.5688298918387416, "grad_norm": 7.395683765411377, "learning_rate": 4.311701081612587e-06, "loss": 0.2939, "step": 10450 }, { "epoch": 2.5712881022615535, "grad_norm": 14.67055606842041, "learning_rate": 4.2871189773844646e-06, "loss": 0.3303, "step": 10460 }, { "epoch": 2.573746312684366, "grad_norm": 7.944691181182861, "learning_rate": 4.262536873156342e-06, "loss": 0.3013, "step": 10470 }, { "epoch": 2.5762045231071777, "grad_norm": 4.720646381378174, "learning_rate": 4.23795476892822e-06, "loss": 0.2919, "step": 10480 }, { "epoch": 2.57866273352999, "grad_norm": 15.954136848449707, "learning_rate": 4.213372664700098e-06, "loss": 0.4517, "step": 10490 }, { "epoch": 2.5811209439528024, "grad_norm": 5.896755695343018, "learning_rate": 4.188790560471976e-06, "loss": 0.1998, "step": 10500 }, { "epoch": 2.583579154375615, "grad_norm": 21.094676971435547, "learning_rate": 4.164208456243854e-06, "loss": 0.3074, "step": 10510 }, { "epoch": 2.5860373647984267, "grad_norm": 6.191657543182373, "learning_rate": 4.139626352015732e-06, "loss": 0.3241, "step": 10520 }, { "epoch": 2.588495575221239, "grad_norm": 20.344154357910156, "learning_rate": 4.115044247787611e-06, "loss": 0.3347, "step": 10530 }, { "epoch": 2.590953785644051, "grad_norm": 8.485753059387207, "learning_rate": 4.090462143559489e-06, "loss": 0.2511, "step": 10540 }, { "epoch": 2.5934119960668633, "grad_norm": 15.798835754394531, "learning_rate": 4.0658800393313665e-06, "loss": 0.3782, "step": 10550 }, { "epoch": 2.5958702064896757, "grad_norm": 13.391433715820312, "learning_rate": 4.041297935103244e-06, "loss": 0.2083, "step": 10560 }, { "epoch": 2.5983284169124876, "grad_norm": 7.110270977020264, "learning_rate": 4.016715830875123e-06, "loss": 0.3041, "step": 10570 }, { "epoch": 2.6007866273353, "grad_norm": 8.893359184265137, "learning_rate": 3.992133726647001e-06, "loss": 0.2461, "step": 10580 }, { "epoch": 2.603244837758112, "grad_norm": 7.249054908752441, "learning_rate": 3.967551622418879e-06, "loss": 0.2148, "step": 10590 }, { "epoch": 2.6057030481809242, "grad_norm": 14.97016716003418, "learning_rate": 3.942969518190757e-06, "loss": 0.3016, "step": 10600 }, { "epoch": 2.6081612586037366, "grad_norm": 15.741162300109863, "learning_rate": 3.918387413962636e-06, "loss": 0.2568, "step": 10610 }, { "epoch": 2.6106194690265485, "grad_norm": 12.992851257324219, "learning_rate": 3.8938053097345135e-06, "loss": 0.2923, "step": 10620 }, { "epoch": 2.613077679449361, "grad_norm": 9.145554542541504, "learning_rate": 3.869223205506391e-06, "loss": 0.3393, "step": 10630 }, { "epoch": 2.615535889872173, "grad_norm": 9.965248107910156, "learning_rate": 3.844641101278269e-06, "loss": 0.2694, "step": 10640 }, { "epoch": 2.617994100294985, "grad_norm": 15.187629699707031, "learning_rate": 3.820058997050147e-06, "loss": 0.2652, "step": 10650 }, { "epoch": 2.6204523107177975, "grad_norm": 4.811568260192871, "learning_rate": 3.7954768928220255e-06, "loss": 0.3524, "step": 10660 }, { "epoch": 2.62291052114061, "grad_norm": 16.703216552734375, "learning_rate": 3.770894788593904e-06, "loss": 0.3127, "step": 10670 }, { "epoch": 2.6253687315634218, "grad_norm": 10.77552318572998, "learning_rate": 3.7463126843657817e-06, "loss": 0.3132, "step": 10680 }, { "epoch": 2.627826941986234, "grad_norm": 7.146244049072266, "learning_rate": 3.72173058013766e-06, "loss": 0.2765, "step": 10690 }, { "epoch": 2.630285152409046, "grad_norm": 2.7346856594085693, "learning_rate": 3.697148475909538e-06, "loss": 0.3273, "step": 10700 }, { "epoch": 2.6327433628318584, "grad_norm": 9.601373672485352, "learning_rate": 3.6725663716814163e-06, "loss": 0.3604, "step": 10710 }, { "epoch": 2.6352015732546707, "grad_norm": 17.365041732788086, "learning_rate": 3.647984267453294e-06, "loss": 0.3601, "step": 10720 }, { "epoch": 2.6376597836774827, "grad_norm": 15.590822219848633, "learning_rate": 3.6234021632251725e-06, "loss": 0.3188, "step": 10730 }, { "epoch": 2.640117994100295, "grad_norm": 1.0473146438598633, "learning_rate": 3.59882005899705e-06, "loss": 0.2012, "step": 10740 }, { "epoch": 2.642576204523107, "grad_norm": 8.146947860717773, "learning_rate": 3.5742379547689283e-06, "loss": 0.1998, "step": 10750 }, { "epoch": 2.6450344149459193, "grad_norm": 23.926929473876953, "learning_rate": 3.549655850540806e-06, "loss": 0.4045, "step": 10760 }, { "epoch": 2.6474926253687316, "grad_norm": 3.894239902496338, "learning_rate": 3.5250737463126845e-06, "loss": 0.3048, "step": 10770 }, { "epoch": 2.649950835791544, "grad_norm": 13.886688232421875, "learning_rate": 3.5004916420845624e-06, "loss": 0.2222, "step": 10780 }, { "epoch": 2.652409046214356, "grad_norm": 12.490795135498047, "learning_rate": 3.4759095378564403e-06, "loss": 0.3086, "step": 10790 }, { "epoch": 2.6548672566371683, "grad_norm": 6.3705949783325195, "learning_rate": 3.4513274336283186e-06, "loss": 0.4504, "step": 10800 }, { "epoch": 2.65732546705998, "grad_norm": 2.8006486892700195, "learning_rate": 3.4267453294001965e-06, "loss": 0.3211, "step": 10810 }, { "epoch": 2.6597836774827925, "grad_norm": 11.899230003356934, "learning_rate": 3.402163225172075e-06, "loss": 0.3668, "step": 10820 }, { "epoch": 2.662241887905605, "grad_norm": 15.25240421295166, "learning_rate": 3.3775811209439528e-06, "loss": 0.2917, "step": 10830 }, { "epoch": 2.664700098328417, "grad_norm": 12.937860488891602, "learning_rate": 3.352999016715831e-06, "loss": 0.2749, "step": 10840 }, { "epoch": 2.667158308751229, "grad_norm": 17.778671264648438, "learning_rate": 3.328416912487709e-06, "loss": 0.4011, "step": 10850 }, { "epoch": 2.669616519174041, "grad_norm": 11.849617958068848, "learning_rate": 3.3038348082595873e-06, "loss": 0.2668, "step": 10860 }, { "epoch": 2.6720747295968534, "grad_norm": 3.560965061187744, "learning_rate": 3.279252704031465e-06, "loss": 0.2715, "step": 10870 }, { "epoch": 2.674532940019666, "grad_norm": 11.311788558959961, "learning_rate": 3.2546705998033435e-06, "loss": 0.2562, "step": 10880 }, { "epoch": 2.676991150442478, "grad_norm": 5.303350925445557, "learning_rate": 3.2300884955752214e-06, "loss": 0.1914, "step": 10890 }, { "epoch": 2.67944936086529, "grad_norm": 8.772753715515137, "learning_rate": 3.2055063913470998e-06, "loss": 0.3124, "step": 10900 }, { "epoch": 2.6819075712881024, "grad_norm": 11.487403869628906, "learning_rate": 3.1809242871189772e-06, "loss": 0.3248, "step": 10910 }, { "epoch": 2.6843657817109143, "grad_norm": 6.985296249389648, "learning_rate": 3.1563421828908556e-06, "loss": 0.208, "step": 10920 }, { "epoch": 2.6868239921337267, "grad_norm": 5.001655101776123, "learning_rate": 3.1317600786627335e-06, "loss": 0.3099, "step": 10930 }, { "epoch": 2.689282202556539, "grad_norm": 5.20217752456665, "learning_rate": 3.1071779744346114e-06, "loss": 0.1859, "step": 10940 }, { "epoch": 2.691740412979351, "grad_norm": 16.58912467956543, "learning_rate": 3.0825958702064897e-06, "loss": 0.2093, "step": 10950 }, { "epoch": 2.6941986234021633, "grad_norm": 11.073062896728516, "learning_rate": 3.0580137659783676e-06, "loss": 0.3691, "step": 10960 }, { "epoch": 2.6966568338249752, "grad_norm": 40.447330474853516, "learning_rate": 3.033431661750246e-06, "loss": 0.275, "step": 10970 }, { "epoch": 2.6991150442477876, "grad_norm": 28.583017349243164, "learning_rate": 3.008849557522124e-06, "loss": 0.4315, "step": 10980 }, { "epoch": 2.7015732546706, "grad_norm": 10.325236320495605, "learning_rate": 2.984267453294002e-06, "loss": 0.2975, "step": 10990 }, { "epoch": 2.704031465093412, "grad_norm": 2.424309253692627, "learning_rate": 2.95968534906588e-06, "loss": 0.2669, "step": 11000 }, { "epoch": 2.706489675516224, "grad_norm": 21.16057014465332, "learning_rate": 2.9351032448377583e-06, "loss": 0.3747, "step": 11010 }, { "epoch": 2.708947885939036, "grad_norm": 10.140483856201172, "learning_rate": 2.9105211406096362e-06, "loss": 0.2489, "step": 11020 }, { "epoch": 2.7114060963618485, "grad_norm": 5.878184795379639, "learning_rate": 2.8859390363815146e-06, "loss": 0.3925, "step": 11030 }, { "epoch": 2.713864306784661, "grad_norm": 11.350957870483398, "learning_rate": 2.8613569321533925e-06, "loss": 0.3155, "step": 11040 }, { "epoch": 2.716322517207473, "grad_norm": 7.840111255645752, "learning_rate": 2.8367748279252708e-06, "loss": 0.3292, "step": 11050 }, { "epoch": 2.718780727630285, "grad_norm": 18.80568504333496, "learning_rate": 2.8121927236971487e-06, "loss": 0.3958, "step": 11060 }, { "epoch": 2.7212389380530975, "grad_norm": 7.600488185882568, "learning_rate": 2.7876106194690266e-06, "loss": 0.3281, "step": 11070 }, { "epoch": 2.7236971484759094, "grad_norm": 4.560182094573975, "learning_rate": 2.763028515240905e-06, "loss": 0.1984, "step": 11080 }, { "epoch": 2.7261553588987217, "grad_norm": 4.8485236167907715, "learning_rate": 2.7384464110127824e-06, "loss": 0.2054, "step": 11090 }, { "epoch": 2.728613569321534, "grad_norm": 15.203032493591309, "learning_rate": 2.7138643067846607e-06, "loss": 0.2609, "step": 11100 }, { "epoch": 2.731071779744346, "grad_norm": 7.723146915435791, "learning_rate": 2.6892822025565386e-06, "loss": 0.1805, "step": 11110 }, { "epoch": 2.7335299901671584, "grad_norm": 7.581287384033203, "learning_rate": 2.664700098328417e-06, "loss": 0.3039, "step": 11120 }, { "epoch": 2.7359882005899703, "grad_norm": 20.293846130371094, "learning_rate": 2.640117994100295e-06, "loss": 0.3652, "step": 11130 }, { "epoch": 2.7384464110127826, "grad_norm": 6.099135398864746, "learning_rate": 2.615535889872173e-06, "loss": 0.3285, "step": 11140 }, { "epoch": 2.740904621435595, "grad_norm": 12.43327522277832, "learning_rate": 2.590953785644051e-06, "loss": 0.2566, "step": 11150 }, { "epoch": 2.7433628318584073, "grad_norm": 11.928936958312988, "learning_rate": 2.5663716814159294e-06, "loss": 0.3206, "step": 11160 }, { "epoch": 2.7458210422812193, "grad_norm": 9.150959014892578, "learning_rate": 2.5417895771878073e-06, "loss": 0.2686, "step": 11170 }, { "epoch": 2.7482792527040316, "grad_norm": 15.1760835647583, "learning_rate": 2.5172074729596856e-06, "loss": 0.3135, "step": 11180 }, { "epoch": 2.7507374631268435, "grad_norm": 1.32634437084198, "learning_rate": 2.4926253687315635e-06, "loss": 0.1764, "step": 11190 }, { "epoch": 2.753195673549656, "grad_norm": 11.577444076538086, "learning_rate": 2.468043264503442e-06, "loss": 0.2989, "step": 11200 }, { "epoch": 2.7556538839724682, "grad_norm": 14.957494735717773, "learning_rate": 2.4434611602753197e-06, "loss": 0.2282, "step": 11210 }, { "epoch": 2.75811209439528, "grad_norm": 21.897722244262695, "learning_rate": 2.4188790560471976e-06, "loss": 0.2881, "step": 11220 }, { "epoch": 2.7605703048180925, "grad_norm": 10.6362943649292, "learning_rate": 2.394296951819076e-06, "loss": 0.3382, "step": 11230 }, { "epoch": 2.7630285152409044, "grad_norm": 27.443620681762695, "learning_rate": 2.369714847590954e-06, "loss": 0.3428, "step": 11240 }, { "epoch": 2.765486725663717, "grad_norm": 3.9533727169036865, "learning_rate": 2.345132743362832e-06, "loss": 0.271, "step": 11250 }, { "epoch": 2.767944936086529, "grad_norm": 1.3611125946044922, "learning_rate": 2.32055063913471e-06, "loss": 0.4512, "step": 11260 }, { "epoch": 2.770403146509341, "grad_norm": 8.420342445373535, "learning_rate": 2.295968534906588e-06, "loss": 0.2286, "step": 11270 }, { "epoch": 2.7728613569321534, "grad_norm": 5.093447208404541, "learning_rate": 2.271386430678466e-06, "loss": 0.2566, "step": 11280 }, { "epoch": 2.7753195673549653, "grad_norm": 6.2292938232421875, "learning_rate": 2.246804326450344e-06, "loss": 0.3357, "step": 11290 }, { "epoch": 2.7777777777777777, "grad_norm": 17.072811126708984, "learning_rate": 2.222222222222222e-06, "loss": 0.3373, "step": 11300 }, { "epoch": 2.78023598820059, "grad_norm": 6.227046489715576, "learning_rate": 2.1976401179941004e-06, "loss": 0.2706, "step": 11310 }, { "epoch": 2.7826941986234024, "grad_norm": 10.372603416442871, "learning_rate": 2.1730580137659783e-06, "loss": 0.2605, "step": 11320 }, { "epoch": 2.7851524090462143, "grad_norm": 9.851338386535645, "learning_rate": 2.1484759095378566e-06, "loss": 0.3035, "step": 11330 }, { "epoch": 2.7876106194690267, "grad_norm": 7.0967698097229, "learning_rate": 2.1238938053097345e-06, "loss": 0.2663, "step": 11340 }, { "epoch": 2.7900688298918386, "grad_norm": 14.124640464782715, "learning_rate": 2.099311701081613e-06, "loss": 0.2406, "step": 11350 }, { "epoch": 2.792527040314651, "grad_norm": 13.570901870727539, "learning_rate": 2.0747295968534907e-06, "loss": 0.2769, "step": 11360 }, { "epoch": 2.7949852507374633, "grad_norm": 10.173891067504883, "learning_rate": 2.0501474926253686e-06, "loss": 0.2492, "step": 11370 }, { "epoch": 2.797443461160275, "grad_norm": 3.0072109699249268, "learning_rate": 2.025565388397247e-06, "loss": 0.3613, "step": 11380 }, { "epoch": 2.7999016715830876, "grad_norm": 15.063048362731934, "learning_rate": 2.000983284169125e-06, "loss": 0.3411, "step": 11390 }, { "epoch": 2.8023598820058995, "grad_norm": 17.408193588256836, "learning_rate": 1.976401179941003e-06, "loss": 0.3041, "step": 11400 }, { "epoch": 2.804818092428712, "grad_norm": 18.045740127563477, "learning_rate": 1.951819075712881e-06, "loss": 0.3198, "step": 11410 }, { "epoch": 2.807276302851524, "grad_norm": 10.629345893859863, "learning_rate": 1.9272369714847594e-06, "loss": 0.2996, "step": 11420 }, { "epoch": 2.8097345132743365, "grad_norm": 5.943514347076416, "learning_rate": 1.9026548672566373e-06, "loss": 0.3009, "step": 11430 }, { "epoch": 2.8121927236971485, "grad_norm": 8.855863571166992, "learning_rate": 1.8780727630285154e-06, "loss": 0.4175, "step": 11440 }, { "epoch": 2.814650934119961, "grad_norm": 15.385708808898926, "learning_rate": 1.8534906588003933e-06, "loss": 0.3439, "step": 11450 }, { "epoch": 2.8171091445427727, "grad_norm": 3.6414332389831543, "learning_rate": 1.8289085545722714e-06, "loss": 0.2678, "step": 11460 }, { "epoch": 2.819567354965585, "grad_norm": 20.068828582763672, "learning_rate": 1.8043264503441495e-06, "loss": 0.2691, "step": 11470 }, { "epoch": 2.8220255653883974, "grad_norm": 12.524300575256348, "learning_rate": 1.7797443461160276e-06, "loss": 0.2174, "step": 11480 }, { "epoch": 2.8244837758112094, "grad_norm": 5.774837493896484, "learning_rate": 1.7551622418879055e-06, "loss": 0.2994, "step": 11490 }, { "epoch": 2.8269419862340217, "grad_norm": 16.437944412231445, "learning_rate": 1.7305801376597837e-06, "loss": 0.3399, "step": 11500 }, { "epoch": 2.8294001966568336, "grad_norm": 4.395741939544678, "learning_rate": 1.7059980334316618e-06, "loss": 0.2161, "step": 11510 }, { "epoch": 2.831858407079646, "grad_norm": 3.2524924278259277, "learning_rate": 1.6814159292035399e-06, "loss": 0.2456, "step": 11520 }, { "epoch": 2.8343166175024583, "grad_norm": 12.618989944458008, "learning_rate": 1.656833824975418e-06, "loss": 0.2965, "step": 11530 }, { "epoch": 2.8367748279252702, "grad_norm": 5.8480939865112305, "learning_rate": 1.632251720747296e-06, "loss": 0.2249, "step": 11540 }, { "epoch": 2.8392330383480826, "grad_norm": 17.862777709960938, "learning_rate": 1.6076696165191742e-06, "loss": 0.2915, "step": 11550 }, { "epoch": 2.8416912487708945, "grad_norm": 14.191113471984863, "learning_rate": 1.5830875122910523e-06, "loss": 0.3229, "step": 11560 }, { "epoch": 2.844149459193707, "grad_norm": 4.146345138549805, "learning_rate": 1.5585054080629302e-06, "loss": 0.3202, "step": 11570 }, { "epoch": 2.8466076696165192, "grad_norm": 5.556818008422852, "learning_rate": 1.5339233038348081e-06, "loss": 0.3213, "step": 11580 }, { "epoch": 2.8490658800393316, "grad_norm": 8.353351593017578, "learning_rate": 1.5093411996066862e-06, "loss": 0.411, "step": 11590 }, { "epoch": 2.8515240904621435, "grad_norm": 23.286680221557617, "learning_rate": 1.4847590953785643e-06, "loss": 0.408, "step": 11600 }, { "epoch": 2.853982300884956, "grad_norm": 19.07876968383789, "learning_rate": 1.4601769911504425e-06, "loss": 0.3691, "step": 11610 }, { "epoch": 2.8564405113077678, "grad_norm": 6.385343074798584, "learning_rate": 1.4355948869223206e-06, "loss": 0.3131, "step": 11620 }, { "epoch": 2.85889872173058, "grad_norm": 19.484460830688477, "learning_rate": 1.4110127826941987e-06, "loss": 0.3574, "step": 11630 }, { "epoch": 2.8613569321533925, "grad_norm": 12.295538902282715, "learning_rate": 1.3864306784660768e-06, "loss": 0.224, "step": 11640 }, { "epoch": 2.8638151425762044, "grad_norm": 5.19575834274292, "learning_rate": 1.361848574237955e-06, "loss": 0.3497, "step": 11650 }, { "epoch": 2.8662733529990168, "grad_norm": 12.624898910522461, "learning_rate": 1.337266470009833e-06, "loss": 0.3325, "step": 11660 }, { "epoch": 2.8687315634218287, "grad_norm": 10.314776420593262, "learning_rate": 1.312684365781711e-06, "loss": 0.2921, "step": 11670 }, { "epoch": 2.871189773844641, "grad_norm": 24.278417587280273, "learning_rate": 1.288102261553589e-06, "loss": 0.2505, "step": 11680 }, { "epoch": 2.8736479842674534, "grad_norm": 7.0600666999816895, "learning_rate": 1.2635201573254671e-06, "loss": 0.2758, "step": 11690 }, { "epoch": 2.8761061946902657, "grad_norm": 5.888333797454834, "learning_rate": 1.2389380530973452e-06, "loss": 0.2326, "step": 11700 }, { "epoch": 2.8785644051130777, "grad_norm": 9.48932933807373, "learning_rate": 1.2143559488692231e-06, "loss": 0.2206, "step": 11710 }, { "epoch": 2.88102261553589, "grad_norm": 10.436245918273926, "learning_rate": 1.1897738446411013e-06, "loss": 0.2619, "step": 11720 }, { "epoch": 2.883480825958702, "grad_norm": 17.94244384765625, "learning_rate": 1.1651917404129794e-06, "loss": 0.3894, "step": 11730 }, { "epoch": 2.8859390363815143, "grad_norm": 7.205624580383301, "learning_rate": 1.1406096361848575e-06, "loss": 0.2692, "step": 11740 }, { "epoch": 2.8883972468043266, "grad_norm": 15.906659126281738, "learning_rate": 1.1160275319567356e-06, "loss": 0.3353, "step": 11750 }, { "epoch": 2.8908554572271385, "grad_norm": 10.102609634399414, "learning_rate": 1.0914454277286135e-06, "loss": 0.3815, "step": 11760 }, { "epoch": 2.893313667649951, "grad_norm": 3.915815830230713, "learning_rate": 1.0668633235004916e-06, "loss": 0.2158, "step": 11770 }, { "epoch": 2.895771878072763, "grad_norm": 3.3347067832946777, "learning_rate": 1.0422812192723697e-06, "loss": 0.211, "step": 11780 }, { "epoch": 2.898230088495575, "grad_norm": 14.25108814239502, "learning_rate": 1.0176991150442478e-06, "loss": 0.339, "step": 11790 }, { "epoch": 2.9006882989183875, "grad_norm": 1.4729186296463013, "learning_rate": 9.93117010816126e-07, "loss": 0.2707, "step": 11800 }, { "epoch": 2.9031465093411994, "grad_norm": 13.042509078979492, "learning_rate": 9.68534906588004e-07, "loss": 0.2246, "step": 11810 }, { "epoch": 2.905604719764012, "grad_norm": 9.084315299987793, "learning_rate": 9.43952802359882e-07, "loss": 0.304, "step": 11820 }, { "epoch": 2.908062930186824, "grad_norm": 16.768390655517578, "learning_rate": 9.1937069813176e-07, "loss": 0.2658, "step": 11830 }, { "epoch": 2.910521140609636, "grad_norm": 18.188396453857422, "learning_rate": 8.947885939036382e-07, "loss": 0.3729, "step": 11840 }, { "epoch": 2.9129793510324484, "grad_norm": 7.643548011779785, "learning_rate": 8.702064896755163e-07, "loss": 0.3021, "step": 11850 }, { "epoch": 2.915437561455261, "grad_norm": 16.475297927856445, "learning_rate": 8.456243854473944e-07, "loss": 0.2954, "step": 11860 }, { "epoch": 2.9178957718780727, "grad_norm": 4.122929096221924, "learning_rate": 8.210422812192724e-07, "loss": 0.348, "step": 11870 }, { "epoch": 2.920353982300885, "grad_norm": 27.607580184936523, "learning_rate": 7.964601769911505e-07, "loss": 0.3595, "step": 11880 }, { "epoch": 2.922812192723697, "grad_norm": 17.518573760986328, "learning_rate": 7.718780727630285e-07, "loss": 0.2807, "step": 11890 }, { "epoch": 2.9252704031465093, "grad_norm": 2.8350279331207275, "learning_rate": 7.472959685349066e-07, "loss": 0.1872, "step": 11900 }, { "epoch": 2.9277286135693217, "grad_norm": 13.840428352355957, "learning_rate": 7.227138643067846e-07, "loss": 0.2673, "step": 11910 }, { "epoch": 2.9301868239921336, "grad_norm": 8.021927833557129, "learning_rate": 6.981317600786627e-07, "loss": 0.2909, "step": 11920 }, { "epoch": 2.932645034414946, "grad_norm": 6.063304901123047, "learning_rate": 6.735496558505408e-07, "loss": 0.3615, "step": 11930 }, { "epoch": 2.935103244837758, "grad_norm": 7.167562484741211, "learning_rate": 6.48967551622419e-07, "loss": 0.227, "step": 11940 }, { "epoch": 2.93756145526057, "grad_norm": 10.438478469848633, "learning_rate": 6.243854473942971e-07, "loss": 0.2487, "step": 11950 }, { "epoch": 2.9400196656833826, "grad_norm": 9.834517478942871, "learning_rate": 5.99803343166175e-07, "loss": 0.2863, "step": 11960 }, { "epoch": 2.942477876106195, "grad_norm": 7.601406097412109, "learning_rate": 5.752212389380531e-07, "loss": 0.3034, "step": 11970 }, { "epoch": 2.944936086529007, "grad_norm": 9.009343147277832, "learning_rate": 5.506391347099312e-07, "loss": 0.2632, "step": 11980 }, { "epoch": 2.947394296951819, "grad_norm": 21.899898529052734, "learning_rate": 5.260570304818093e-07, "loss": 0.2246, "step": 11990 }, { "epoch": 2.949852507374631, "grad_norm": 23.268657684326172, "learning_rate": 5.014749262536873e-07, "loss": 0.2524, "step": 12000 }, { "epoch": 2.9523107177974435, "grad_norm": 11.325539588928223, "learning_rate": 4.768928220255654e-07, "loss": 0.3792, "step": 12010 }, { "epoch": 2.954768928220256, "grad_norm": 17.498369216918945, "learning_rate": 4.5231071779744347e-07, "loss": 0.3055, "step": 12020 }, { "epoch": 2.9572271386430677, "grad_norm": 5.532654762268066, "learning_rate": 4.277286135693215e-07, "loss": 0.3094, "step": 12030 }, { "epoch": 2.95968534906588, "grad_norm": 11.48263168334961, "learning_rate": 4.0314650934119964e-07, "loss": 0.2827, "step": 12040 }, { "epoch": 2.962143559488692, "grad_norm": 22.20387077331543, "learning_rate": 3.785644051130777e-07, "loss": 0.27, "step": 12050 }, { "epoch": 2.9646017699115044, "grad_norm": 6.053637504577637, "learning_rate": 3.5398230088495575e-07, "loss": 0.3132, "step": 12060 }, { "epoch": 2.9670599803343167, "grad_norm": 13.215700149536133, "learning_rate": 3.2940019665683386e-07, "loss": 0.2593, "step": 12070 }, { "epoch": 2.969518190757129, "grad_norm": 14.301483154296875, "learning_rate": 3.0481809242871187e-07, "loss": 0.184, "step": 12080 }, { "epoch": 2.971976401179941, "grad_norm": 4.257253170013428, "learning_rate": 2.8023598820059e-07, "loss": 0.2439, "step": 12090 }, { "epoch": 2.9744346116027534, "grad_norm": 10.859535217285156, "learning_rate": 2.5565388397246804e-07, "loss": 0.3386, "step": 12100 }, { "epoch": 2.9768928220255653, "grad_norm": 8.786941528320312, "learning_rate": 2.3107177974434612e-07, "loss": 0.325, "step": 12110 }, { "epoch": 2.9793510324483776, "grad_norm": 13.41217041015625, "learning_rate": 2.064896755162242e-07, "loss": 0.2705, "step": 12120 }, { "epoch": 2.98180924287119, "grad_norm": 6.551536560058594, "learning_rate": 1.8190757128810226e-07, "loss": 0.2342, "step": 12130 }, { "epoch": 2.984267453294002, "grad_norm": 12.792823791503906, "learning_rate": 1.5732546705998035e-07, "loss": 0.2762, "step": 12140 }, { "epoch": 2.9867256637168142, "grad_norm": 12.206270217895508, "learning_rate": 1.327433628318584e-07, "loss": 0.2987, "step": 12150 }, { "epoch": 2.989183874139626, "grad_norm": 10.073808670043945, "learning_rate": 1.0816125860373648e-07, "loss": 0.3221, "step": 12160 }, { "epoch": 2.9916420845624385, "grad_norm": 7.215149402618408, "learning_rate": 8.357915437561456e-08, "loss": 0.3088, "step": 12170 }, { "epoch": 2.994100294985251, "grad_norm": 9.318428039550781, "learning_rate": 5.899705014749263e-08, "loss": 0.4131, "step": 12180 }, { "epoch": 2.996558505408063, "grad_norm": 11.540080070495605, "learning_rate": 3.44149459193707e-08, "loss": 0.2204, "step": 12190 }, { "epoch": 2.999016715830875, "grad_norm": 8.453729629516602, "learning_rate": 9.832841691248772e-09, "loss": 0.2731, "step": 12200 }, { "epoch": 3.0, "eval_accuracy": 0.848845249619693, "eval_f1_score": 0.8480515271470224, "eval_loss": 0.45648908615112305, "eval_runtime": 115.6033, "eval_samples_per_second": 62.55, "eval_steps_per_second": 3.91, "step": 12204 } ], "logging_steps": 10, "max_steps": 12204, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.137006864037069e+16, "train_batch_size": 16, "trial_name": null, "trial_params": null }