{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.9260969976905313, "eval_steps": 500, "global_step": 8500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004618937644341801, "grad_norm": 11.009225845336914, "learning_rate": 5.773672055427253e-07, "loss": 2.4977, "step": 10 }, { "epoch": 0.009237875288683603, "grad_norm": 9.019889831542969, "learning_rate": 1.1547344110854505e-06, "loss": 2.7655, "step": 20 }, { "epoch": 0.013856812933025405, "grad_norm": 11.212933540344238, "learning_rate": 1.7321016166281756e-06, "loss": 2.7241, "step": 30 }, { "epoch": 0.018475750577367205, "grad_norm": 9.982237815856934, "learning_rate": 2.309468822170901e-06, "loss": 2.8357, "step": 40 }, { "epoch": 0.023094688221709007, "grad_norm": 16.251842498779297, "learning_rate": 2.886836027713626e-06, "loss": 2.1159, "step": 50 }, { "epoch": 0.02771362586605081, "grad_norm": 7.950500011444092, "learning_rate": 3.464203233256351e-06, "loss": 1.498, "step": 60 }, { "epoch": 0.03233256351039261, "grad_norm": 4.816328048706055, "learning_rate": 4.041570438799077e-06, "loss": 0.9835, "step": 70 }, { "epoch": 0.03695150115473441, "grad_norm": 9.529770851135254, "learning_rate": 4.618937644341802e-06, "loss": 1.0009, "step": 80 }, { "epoch": 0.04157043879907621, "grad_norm": 12.515681266784668, "learning_rate": 5.196304849884527e-06, "loss": 1.0264, "step": 90 }, { "epoch": 0.046189376443418015, "grad_norm": 5.393396854400635, "learning_rate": 5.773672055427252e-06, "loss": 0.8218, "step": 100 }, { "epoch": 0.050808314087759814, "grad_norm": 2.777273416519165, "learning_rate": 6.351039260969978e-06, "loss": 0.8719, "step": 110 }, { "epoch": 0.05542725173210162, "grad_norm": 3.8990070819854736, "learning_rate": 6.928406466512702e-06, "loss": 0.8592, "step": 120 }, { "epoch": 0.06004618937644342, "grad_norm": 4.342905521392822, "learning_rate": 7.505773672055427e-06, "loss": 0.7982, "step": 130 }, { "epoch": 0.06466512702078522, "grad_norm": 2.4967517852783203, "learning_rate": 8.083140877598153e-06, "loss": 0.7203, "step": 140 }, { "epoch": 0.06928406466512702, "grad_norm": 5.491476058959961, "learning_rate": 8.660508083140878e-06, "loss": 0.7647, "step": 150 }, { "epoch": 0.07390300230946882, "grad_norm": 4.13068962097168, "learning_rate": 9.237875288683604e-06, "loss": 0.7378, "step": 160 }, { "epoch": 0.07852193995381063, "grad_norm": 3.9301445484161377, "learning_rate": 9.815242494226329e-06, "loss": 0.7355, "step": 170 }, { "epoch": 0.08314087759815242, "grad_norm": 2.891854763031006, "learning_rate": 1.0392609699769053e-05, "loss": 0.6911, "step": 180 }, { "epoch": 0.08775981524249422, "grad_norm": 5.377829074859619, "learning_rate": 1.0969976905311778e-05, "loss": 0.7972, "step": 190 }, { "epoch": 0.09237875288683603, "grad_norm": 3.1744544506073, "learning_rate": 1.1547344110854504e-05, "loss": 0.6792, "step": 200 }, { "epoch": 0.09699769053117784, "grad_norm": 4.408601760864258, "learning_rate": 1.2124711316397229e-05, "loss": 0.7378, "step": 210 }, { "epoch": 0.10161662817551963, "grad_norm": 3.3633627891540527, "learning_rate": 1.2702078521939955e-05, "loss": 0.7131, "step": 220 }, { "epoch": 0.10623556581986143, "grad_norm": 5.786050319671631, "learning_rate": 1.3279445727482678e-05, "loss": 0.6806, "step": 230 }, { "epoch": 0.11085450346420324, "grad_norm": 6.865295886993408, "learning_rate": 1.3856812933025404e-05, "loss": 0.7117, "step": 240 }, { "epoch": 0.11547344110854503, "grad_norm": 3.714210033416748, "learning_rate": 1.4434180138568129e-05, "loss": 0.6354, "step": 250 }, { "epoch": 0.12009237875288684, "grad_norm": 5.501813888549805, "learning_rate": 1.5011547344110854e-05, "loss": 0.6266, "step": 260 }, { "epoch": 0.12471131639722864, "grad_norm": 6.622759819030762, "learning_rate": 1.558891454965358e-05, "loss": 0.6894, "step": 270 }, { "epoch": 0.12933025404157045, "grad_norm": 3.647956609725952, "learning_rate": 1.6166281755196306e-05, "loss": 0.66, "step": 280 }, { "epoch": 0.13394919168591224, "grad_norm": 4.103866100311279, "learning_rate": 1.674364896073903e-05, "loss": 0.665, "step": 290 }, { "epoch": 0.13856812933025403, "grad_norm": 3.84169340133667, "learning_rate": 1.7321016166281756e-05, "loss": 0.6676, "step": 300 }, { "epoch": 0.14318706697459585, "grad_norm": 8.042781829833984, "learning_rate": 1.789838337182448e-05, "loss": 0.6236, "step": 310 }, { "epoch": 0.14780600461893764, "grad_norm": 4.35403299331665, "learning_rate": 1.8475750577367208e-05, "loss": 0.6283, "step": 320 }, { "epoch": 0.15242494226327943, "grad_norm": 3.7114272117614746, "learning_rate": 1.9053117782909933e-05, "loss": 0.6472, "step": 330 }, { "epoch": 0.15704387990762125, "grad_norm": 2.5825653076171875, "learning_rate": 1.9630484988452657e-05, "loss": 0.6139, "step": 340 }, { "epoch": 0.16166281755196305, "grad_norm": 4.71831750869751, "learning_rate": 2.0207852193995382e-05, "loss": 0.6019, "step": 350 }, { "epoch": 0.16628175519630484, "grad_norm": 7.264115333557129, "learning_rate": 2.0785219399538107e-05, "loss": 0.6484, "step": 360 }, { "epoch": 0.17090069284064666, "grad_norm": 5.484978199005127, "learning_rate": 2.1362586605080835e-05, "loss": 0.6423, "step": 370 }, { "epoch": 0.17551963048498845, "grad_norm": 4.004003524780273, "learning_rate": 2.1939953810623556e-05, "loss": 0.6167, "step": 380 }, { "epoch": 0.18013856812933027, "grad_norm": 3.858074426651001, "learning_rate": 2.251732101616628e-05, "loss": 0.6029, "step": 390 }, { "epoch": 0.18475750577367206, "grad_norm": 4.84448766708374, "learning_rate": 2.309468822170901e-05, "loss": 0.5511, "step": 400 }, { "epoch": 0.18937644341801385, "grad_norm": 3.419329881668091, "learning_rate": 2.3672055427251733e-05, "loss": 0.5919, "step": 410 }, { "epoch": 0.19399538106235567, "grad_norm": 2.367598295211792, "learning_rate": 2.4249422632794458e-05, "loss": 0.5407, "step": 420 }, { "epoch": 0.19861431870669746, "grad_norm": 4.016935348510742, "learning_rate": 2.4826789838337182e-05, "loss": 0.5829, "step": 430 }, { "epoch": 0.20323325635103925, "grad_norm": 4.788145065307617, "learning_rate": 2.540415704387991e-05, "loss": 0.593, "step": 440 }, { "epoch": 0.20785219399538107, "grad_norm": 3.618800401687622, "learning_rate": 2.5981524249422635e-05, "loss": 0.56, "step": 450 }, { "epoch": 0.21247113163972287, "grad_norm": 3.6879987716674805, "learning_rate": 2.6558891454965356e-05, "loss": 0.5448, "step": 460 }, { "epoch": 0.21709006928406466, "grad_norm": 3.6736364364624023, "learning_rate": 2.7136258660508084e-05, "loss": 0.5707, "step": 470 }, { "epoch": 0.22170900692840648, "grad_norm": 3.954604387283325, "learning_rate": 2.771362586605081e-05, "loss": 0.5891, "step": 480 }, { "epoch": 0.22632794457274827, "grad_norm": 6.050353050231934, "learning_rate": 2.8290993071593537e-05, "loss": 0.6231, "step": 490 }, { "epoch": 0.23094688221709006, "grad_norm": 3.728318214416504, "learning_rate": 2.8868360277136258e-05, "loss": 0.6294, "step": 500 }, { "epoch": 0.23556581986143188, "grad_norm": 5.047093391418457, "learning_rate": 2.9445727482678986e-05, "loss": 0.5795, "step": 510 }, { "epoch": 0.24018475750577367, "grad_norm": 4.392754077911377, "learning_rate": 3.0023094688221707e-05, "loss": 0.5634, "step": 520 }, { "epoch": 0.24480369515011546, "grad_norm": 3.634922504425049, "learning_rate": 3.060046189376444e-05, "loss": 0.5372, "step": 530 }, { "epoch": 0.24942263279445728, "grad_norm": 3.2436106204986572, "learning_rate": 3.117782909930716e-05, "loss": 0.5914, "step": 540 }, { "epoch": 0.2540415704387991, "grad_norm": 4.555751323699951, "learning_rate": 3.175519630484989e-05, "loss": 0.5767, "step": 550 }, { "epoch": 0.2586605080831409, "grad_norm": 3.359252452850342, "learning_rate": 3.233256351039261e-05, "loss": 0.5569, "step": 560 }, { "epoch": 0.2632794457274827, "grad_norm": 3.362272262573242, "learning_rate": 3.290993071593534e-05, "loss": 0.6248, "step": 570 }, { "epoch": 0.2678983833718245, "grad_norm": 3.1555299758911133, "learning_rate": 3.348729792147806e-05, "loss": 0.5629, "step": 580 }, { "epoch": 0.27251732101616627, "grad_norm": 4.786733627319336, "learning_rate": 3.4064665127020787e-05, "loss": 0.5942, "step": 590 }, { "epoch": 0.27713625866050806, "grad_norm": 4.290501117706299, "learning_rate": 3.464203233256351e-05, "loss": 0.5694, "step": 600 }, { "epoch": 0.2817551963048499, "grad_norm": 2.2575786113739014, "learning_rate": 3.5219399538106236e-05, "loss": 0.5459, "step": 610 }, { "epoch": 0.2863741339491917, "grad_norm": 4.7077484130859375, "learning_rate": 3.579676674364896e-05, "loss": 0.5686, "step": 620 }, { "epoch": 0.2909930715935335, "grad_norm": 3.487034559249878, "learning_rate": 3.6374133949191685e-05, "loss": 0.5185, "step": 630 }, { "epoch": 0.2956120092378753, "grad_norm": 4.230603218078613, "learning_rate": 3.6951501154734416e-05, "loss": 0.5548, "step": 640 }, { "epoch": 0.3002309468822171, "grad_norm": 3.5367519855499268, "learning_rate": 3.7528868360277134e-05, "loss": 0.5658, "step": 650 }, { "epoch": 0.30484988452655887, "grad_norm": 3.3856465816497803, "learning_rate": 3.8106235565819866e-05, "loss": 0.5459, "step": 660 }, { "epoch": 0.3094688221709007, "grad_norm": 3.4272944927215576, "learning_rate": 3.868360277136259e-05, "loss": 0.5823, "step": 670 }, { "epoch": 0.3140877598152425, "grad_norm": 2.7848410606384277, "learning_rate": 3.9260969976905315e-05, "loss": 0.5481, "step": 680 }, { "epoch": 0.3187066974595843, "grad_norm": 2.8584043979644775, "learning_rate": 3.983833718244804e-05, "loss": 0.4907, "step": 690 }, { "epoch": 0.3233256351039261, "grad_norm": 3.9872729778289795, "learning_rate": 4.0415704387990764e-05, "loss": 0.5703, "step": 700 }, { "epoch": 0.3279445727482679, "grad_norm": 4.052183151245117, "learning_rate": 4.099307159353349e-05, "loss": 0.6229, "step": 710 }, { "epoch": 0.3325635103926097, "grad_norm": 3.6171059608459473, "learning_rate": 4.1570438799076213e-05, "loss": 0.5022, "step": 720 }, { "epoch": 0.3371824480369515, "grad_norm": 3.4360239505767822, "learning_rate": 4.214780600461894e-05, "loss": 0.5642, "step": 730 }, { "epoch": 0.3418013856812933, "grad_norm": 3.328563928604126, "learning_rate": 4.272517321016167e-05, "loss": 0.543, "step": 740 }, { "epoch": 0.3464203233256351, "grad_norm": 2.494722843170166, "learning_rate": 4.330254041570439e-05, "loss": 0.5056, "step": 750 }, { "epoch": 0.3510392609699769, "grad_norm": 2.9856996536254883, "learning_rate": 4.387990762124711e-05, "loss": 0.5215, "step": 760 }, { "epoch": 0.3556581986143187, "grad_norm": 3.6510608196258545, "learning_rate": 4.445727482678984e-05, "loss": 0.5418, "step": 770 }, { "epoch": 0.36027713625866054, "grad_norm": 2.837355136871338, "learning_rate": 4.503464203233256e-05, "loss": 0.5197, "step": 780 }, { "epoch": 0.3648960739030023, "grad_norm": 2.4272849559783936, "learning_rate": 4.561200923787529e-05, "loss": 0.5151, "step": 790 }, { "epoch": 0.3695150115473441, "grad_norm": 2.2198147773742676, "learning_rate": 4.618937644341802e-05, "loss": 0.5037, "step": 800 }, { "epoch": 0.3741339491916859, "grad_norm": 3.082343816757202, "learning_rate": 4.676674364896074e-05, "loss": 0.5411, "step": 810 }, { "epoch": 0.3787528868360277, "grad_norm": 2.739429235458374, "learning_rate": 4.7344110854503466e-05, "loss": 0.5034, "step": 820 }, { "epoch": 0.3833718244803695, "grad_norm": 2.8211052417755127, "learning_rate": 4.792147806004619e-05, "loss": 0.5077, "step": 830 }, { "epoch": 0.38799076212471134, "grad_norm": 4.462055683135986, "learning_rate": 4.8498845265588916e-05, "loss": 0.4883, "step": 840 }, { "epoch": 0.39260969976905313, "grad_norm": 2.8090898990631104, "learning_rate": 4.907621247113165e-05, "loss": 0.4918, "step": 850 }, { "epoch": 0.3972286374133949, "grad_norm": 2.787473440170288, "learning_rate": 4.9653579676674365e-05, "loss": 0.4736, "step": 860 }, { "epoch": 0.4018475750577367, "grad_norm": 3.198763132095337, "learning_rate": 4.999996750557592e-05, "loss": 0.5243, "step": 870 }, { "epoch": 0.4064665127020785, "grad_norm": 3.8778421878814697, "learning_rate": 4.9999601944275146e-05, "loss": 0.5206, "step": 880 }, { "epoch": 0.4110854503464203, "grad_norm": 4.326559066772461, "learning_rate": 4.999883020960263e-05, "loss": 0.5998, "step": 890 }, { "epoch": 0.41570438799076215, "grad_norm": 2.1009411811828613, "learning_rate": 4.99976523140969e-05, "loss": 0.5097, "step": 900 }, { "epoch": 0.42032332563510394, "grad_norm": 3.0838584899902344, "learning_rate": 4.999606827689545e-05, "loss": 0.4699, "step": 910 }, { "epoch": 0.42494226327944573, "grad_norm": 3.067430019378662, "learning_rate": 4.999407812373445e-05, "loss": 0.5223, "step": 920 }, { "epoch": 0.4295612009237875, "grad_norm": 2.580418109893799, "learning_rate": 4.9991681886948297e-05, "loss": 0.5396, "step": 930 }, { "epoch": 0.4341801385681293, "grad_norm": 2.748032808303833, "learning_rate": 4.9988879605469106e-05, "loss": 0.4965, "step": 940 }, { "epoch": 0.4387990762124711, "grad_norm": 2.841571569442749, "learning_rate": 4.99856713248261e-05, "loss": 0.472, "step": 950 }, { "epoch": 0.44341801385681295, "grad_norm": 1.8557236194610596, "learning_rate": 4.9982057097144826e-05, "loss": 0.4878, "step": 960 }, { "epoch": 0.44803695150115475, "grad_norm": 5.707876205444336, "learning_rate": 4.9978036981146344e-05, "loss": 0.4883, "step": 970 }, { "epoch": 0.45265588914549654, "grad_norm": 3.867081880569458, "learning_rate": 4.9973611042146254e-05, "loss": 0.4929, "step": 980 }, { "epoch": 0.45727482678983833, "grad_norm": 2.291074275970459, "learning_rate": 4.996877935205365e-05, "loss": 0.5046, "step": 990 }, { "epoch": 0.4618937644341801, "grad_norm": 2.332185745239258, "learning_rate": 4.996354198936993e-05, "loss": 0.4539, "step": 1000 }, { "epoch": 0.4665127020785219, "grad_norm": 3.7381327152252197, "learning_rate": 4.995789903918755e-05, "loss": 0.5296, "step": 1010 }, { "epoch": 0.47113163972286376, "grad_norm": 2.239875078201294, "learning_rate": 4.99518505931886e-05, "loss": 0.5004, "step": 1020 }, { "epoch": 0.47575057736720555, "grad_norm": 3.7051751613616943, "learning_rate": 4.9945396749643356e-05, "loss": 0.5319, "step": 1030 }, { "epoch": 0.48036951501154734, "grad_norm": 2.5135374069213867, "learning_rate": 4.993853761340867e-05, "loss": 0.4952, "step": 1040 }, { "epoch": 0.48498845265588914, "grad_norm": 2.6355159282684326, "learning_rate": 4.993127329592625e-05, "loss": 0.4807, "step": 1050 }, { "epoch": 0.4896073903002309, "grad_norm": 5.0833563804626465, "learning_rate": 4.9923603915220874e-05, "loss": 0.5269, "step": 1060 }, { "epoch": 0.4942263279445728, "grad_norm": 2.4188873767852783, "learning_rate": 4.9915529595898445e-05, "loss": 0.5183, "step": 1070 }, { "epoch": 0.49884526558891457, "grad_norm": 2.623342514038086, "learning_rate": 4.9907050469144e-05, "loss": 0.4928, "step": 1080 }, { "epoch": 0.5034642032332564, "grad_norm": 2.629373073577881, "learning_rate": 4.9898166672719547e-05, "loss": 0.5144, "step": 1090 }, { "epoch": 0.5080831408775982, "grad_norm": 1.6594828367233276, "learning_rate": 4.9888878350961857e-05, "loss": 0.4733, "step": 1100 }, { "epoch": 0.5127020785219399, "grad_norm": 2.773136854171753, "learning_rate": 4.987918565478008e-05, "loss": 0.5054, "step": 1110 }, { "epoch": 0.5173210161662818, "grad_norm": 1.9525351524353027, "learning_rate": 4.9869088741653335e-05, "loss": 0.4454, "step": 1120 }, { "epoch": 0.5219399538106235, "grad_norm": 2.84041166305542, "learning_rate": 4.985858777562812e-05, "loss": 0.4871, "step": 1130 }, { "epoch": 0.5265588914549654, "grad_norm": 2.2563703060150146, "learning_rate": 4.9847682927315656e-05, "loss": 0.4605, "step": 1140 }, { "epoch": 0.5311778290993071, "grad_norm": 3.4986164569854736, "learning_rate": 4.983637437388913e-05, "loss": 0.5281, "step": 1150 }, { "epoch": 0.535796766743649, "grad_norm": 2.7081637382507324, "learning_rate": 4.98246622990808e-05, "loss": 0.4568, "step": 1160 }, { "epoch": 0.5404157043879908, "grad_norm": 3.4630649089813232, "learning_rate": 4.981254689317902e-05, "loss": 0.5351, "step": 1170 }, { "epoch": 0.5450346420323325, "grad_norm": 2.5266454219818115, "learning_rate": 4.9800028353025125e-05, "loss": 0.4378, "step": 1180 }, { "epoch": 0.5496535796766744, "grad_norm": 2.003904104232788, "learning_rate": 4.978710688201026e-05, "loss": 0.4539, "step": 1190 }, { "epoch": 0.5542725173210161, "grad_norm": 3.799851655960083, "learning_rate": 4.9773782690072055e-05, "loss": 0.5349, "step": 1200 }, { "epoch": 0.558891454965358, "grad_norm": 2.7120118141174316, "learning_rate": 4.976005599369126e-05, "loss": 0.4938, "step": 1210 }, { "epoch": 0.5635103926096998, "grad_norm": 2.687408208847046, "learning_rate": 4.974592701588816e-05, "loss": 0.4473, "step": 1220 }, { "epoch": 0.5681293302540416, "grad_norm": 2.5710184574127197, "learning_rate": 4.9731395986218976e-05, "loss": 0.4854, "step": 1230 }, { "epoch": 0.5727482678983834, "grad_norm": 3.5843756198883057, "learning_rate": 4.9716463140772176e-05, "loss": 0.5108, "step": 1240 }, { "epoch": 0.5773672055427251, "grad_norm": 3.0808424949645996, "learning_rate": 4.970112872216459e-05, "loss": 0.4664, "step": 1250 }, { "epoch": 0.581986143187067, "grad_norm": 2.7078258991241455, "learning_rate": 4.968539297953748e-05, "loss": 0.5728, "step": 1260 }, { "epoch": 0.5866050808314087, "grad_norm": 2.1983377933502197, "learning_rate": 4.96692561685525e-05, "loss": 0.4551, "step": 1270 }, { "epoch": 0.5912240184757506, "grad_norm": 3.719346046447754, "learning_rate": 4.9652718551387545e-05, "loss": 0.4358, "step": 1280 }, { "epoch": 0.5958429561200924, "grad_norm": 3.773397207260132, "learning_rate": 4.963578039673248e-05, "loss": 0.3883, "step": 1290 }, { "epoch": 0.6004618937644342, "grad_norm": 2.14461350440979, "learning_rate": 4.961844197978479e-05, "loss": 0.4403, "step": 1300 }, { "epoch": 0.605080831408776, "grad_norm": 3.8363335132598877, "learning_rate": 4.960070358224508e-05, "loss": 0.4753, "step": 1310 }, { "epoch": 0.6096997690531177, "grad_norm": 2.10432505607605, "learning_rate": 4.9582565492312537e-05, "loss": 0.4728, "step": 1320 }, { "epoch": 0.6143187066974596, "grad_norm": 2.5199790000915527, "learning_rate": 4.9564028004680215e-05, "loss": 0.4544, "step": 1330 }, { "epoch": 0.6189376443418014, "grad_norm": 3.8586044311523438, "learning_rate": 4.9545091420530265e-05, "loss": 0.4649, "step": 1340 }, { "epoch": 0.6235565819861432, "grad_norm": 1.9125807285308838, "learning_rate": 4.9525756047529023e-05, "loss": 0.4609, "step": 1350 }, { "epoch": 0.628175519630485, "grad_norm": 2.1655430793762207, "learning_rate": 4.950602219982207e-05, "loss": 0.4832, "step": 1360 }, { "epoch": 0.6327944572748267, "grad_norm": 4.029664993286133, "learning_rate": 4.948589019802901e-05, "loss": 0.4751, "step": 1370 }, { "epoch": 0.6374133949191686, "grad_norm": 2.2781596183776855, "learning_rate": 4.94653603692384e-05, "loss": 0.4691, "step": 1380 }, { "epoch": 0.6420323325635104, "grad_norm": 1.623131513595581, "learning_rate": 4.9444433047002327e-05, "loss": 0.4397, "step": 1390 }, { "epoch": 0.6466512702078522, "grad_norm": 2.9153196811676025, "learning_rate": 4.9423108571331055e-05, "loss": 0.4737, "step": 1400 }, { "epoch": 0.651270207852194, "grad_norm": 3.0765182971954346, "learning_rate": 4.940138728868746e-05, "loss": 0.4329, "step": 1410 }, { "epoch": 0.6558891454965358, "grad_norm": 3.2848074436187744, "learning_rate": 4.937926955198144e-05, "loss": 0.4488, "step": 1420 }, { "epoch": 0.6605080831408776, "grad_norm": 2.2458810806274414, "learning_rate": 4.935675572056413e-05, "loss": 0.4645, "step": 1430 }, { "epoch": 0.6651270207852193, "grad_norm": 2.3431642055511475, "learning_rate": 4.933384616022211e-05, "loss": 0.4492, "step": 1440 }, { "epoch": 0.6697459584295612, "grad_norm": 2.6324145793914795, "learning_rate": 4.931054124317144e-05, "loss": 0.4978, "step": 1450 }, { "epoch": 0.674364896073903, "grad_norm": 2.575723171234131, "learning_rate": 4.928684134805162e-05, "loss": 0.4442, "step": 1460 }, { "epoch": 0.6789838337182448, "grad_norm": 2.842388868331909, "learning_rate": 4.926274685991944e-05, "loss": 0.4412, "step": 1470 }, { "epoch": 0.6836027713625866, "grad_norm": 1.8333570957183838, "learning_rate": 4.9238258170242703e-05, "loss": 0.4655, "step": 1480 }, { "epoch": 0.6882217090069284, "grad_norm": 2.276472806930542, "learning_rate": 4.921337567689389e-05, "loss": 0.3944, "step": 1490 }, { "epoch": 0.6928406466512702, "grad_norm": 2.947540760040283, "learning_rate": 4.91880997841437e-05, "loss": 0.4545, "step": 1500 }, { "epoch": 0.6974595842956121, "grad_norm": 2.092616558074951, "learning_rate": 4.916243090265444e-05, "loss": 0.4202, "step": 1510 }, { "epoch": 0.7020785219399538, "grad_norm": 2.4105489253997803, "learning_rate": 4.91363694494734e-05, "loss": 0.4488, "step": 1520 }, { "epoch": 0.7066974595842956, "grad_norm": 2.499821662902832, "learning_rate": 4.910991584802606e-05, "loss": 0.4599, "step": 1530 }, { "epoch": 0.7113163972286374, "grad_norm": 1.7518564462661743, "learning_rate": 4.9083070528109195e-05, "loss": 0.4469, "step": 1540 }, { "epoch": 0.7159353348729792, "grad_norm": 1.6236387491226196, "learning_rate": 4.905583392588392e-05, "loss": 0.4756, "step": 1550 }, { "epoch": 0.7205542725173211, "grad_norm": 3.137925624847412, "learning_rate": 4.902820648386858e-05, "loss": 0.4793, "step": 1560 }, { "epoch": 0.7251732101616628, "grad_norm": 2.584268093109131, "learning_rate": 4.900018865093158e-05, "loss": 0.4445, "step": 1570 }, { "epoch": 0.7297921478060047, "grad_norm": 2.1350574493408203, "learning_rate": 4.897178088228406e-05, "loss": 0.4422, "step": 1580 }, { "epoch": 0.7344110854503464, "grad_norm": 2.1932408809661865, "learning_rate": 4.8942983639472554e-05, "loss": 0.4386, "step": 1590 }, { "epoch": 0.7390300230946882, "grad_norm": 2.0968682765960693, "learning_rate": 4.891379739037142e-05, "loss": 0.4321, "step": 1600 }, { "epoch": 0.74364896073903, "grad_norm": 1.718479037284851, "learning_rate": 4.888422260917532e-05, "loss": 0.4422, "step": 1610 }, { "epoch": 0.7482678983833718, "grad_norm": 2.742122173309326, "learning_rate": 4.885425977639143e-05, "loss": 0.4118, "step": 1620 }, { "epoch": 0.7528868360277137, "grad_norm": 3.560037136077881, "learning_rate": 4.8823909378831694e-05, "loss": 0.4352, "step": 1630 }, { "epoch": 0.7575057736720554, "grad_norm": 1.751957654953003, "learning_rate": 4.8793171909604904e-05, "loss": 0.4222, "step": 1640 }, { "epoch": 0.7621247113163973, "grad_norm": 2.7816951274871826, "learning_rate": 4.876204786810867e-05, "loss": 0.4458, "step": 1650 }, { "epoch": 0.766743648960739, "grad_norm": 1.7703163623809814, "learning_rate": 4.873053776002133e-05, "loss": 0.4387, "step": 1660 }, { "epoch": 0.7713625866050808, "grad_norm": 1.7305679321289062, "learning_rate": 4.8698642097293684e-05, "loss": 0.4203, "step": 1670 }, { "epoch": 0.7759815242494227, "grad_norm": 2.028597116470337, "learning_rate": 4.866636139814076e-05, "loss": 0.4445, "step": 1680 }, { "epoch": 0.7806004618937644, "grad_norm": 2.1649012565612793, "learning_rate": 4.863369618703331e-05, "loss": 0.4392, "step": 1690 }, { "epoch": 0.7852193995381063, "grad_norm": 1.9613428115844727, "learning_rate": 4.860064699468935e-05, "loss": 0.4128, "step": 1700 }, { "epoch": 0.789838337182448, "grad_norm": 1.6601072549819946, "learning_rate": 4.85672143580655e-05, "loss": 0.4211, "step": 1710 }, { "epoch": 0.7944572748267898, "grad_norm": 1.360724925994873, "learning_rate": 4.85333988203483e-05, "loss": 0.4641, "step": 1720 }, { "epoch": 0.7990762124711316, "grad_norm": 1.8491480350494385, "learning_rate": 4.84992009309453e-05, "loss": 0.4466, "step": 1730 }, { "epoch": 0.8036951501154734, "grad_norm": 3.4997713565826416, "learning_rate": 4.8464621245476254e-05, "loss": 0.3786, "step": 1740 }, { "epoch": 0.8083140877598153, "grad_norm": 1.9356039762496948, "learning_rate": 4.8429660325764e-05, "loss": 0.3948, "step": 1750 }, { "epoch": 0.812933025404157, "grad_norm": 1.8650673627853394, "learning_rate": 4.8394318739825364e-05, "loss": 0.3733, "step": 1760 }, { "epoch": 0.8175519630484989, "grad_norm": 2.526487112045288, "learning_rate": 4.835859706186193e-05, "loss": 0.4702, "step": 1770 }, { "epoch": 0.8221709006928406, "grad_norm": 2.5216803550720215, "learning_rate": 4.832249587225073e-05, "loss": 0.4268, "step": 1780 }, { "epoch": 0.8267898383371824, "grad_norm": 3.427783966064453, "learning_rate": 4.828601575753476e-05, "loss": 0.4198, "step": 1790 }, { "epoch": 0.8314087759815243, "grad_norm": 2.734025001525879, "learning_rate": 4.824915731041352e-05, "loss": 0.4305, "step": 1800 }, { "epoch": 0.836027713625866, "grad_norm": 1.9482347965240479, "learning_rate": 4.821192112973333e-05, "loss": 0.4373, "step": 1810 }, { "epoch": 0.8406466512702079, "grad_norm": 2.4370124340057373, "learning_rate": 4.817430782047762e-05, "loss": 0.4477, "step": 1820 }, { "epoch": 0.8452655889145496, "grad_norm": 2.8961851596832275, "learning_rate": 4.8136317993757114e-05, "loss": 0.4611, "step": 1830 }, { "epoch": 0.8498845265588915, "grad_norm": 2.3259379863739014, "learning_rate": 4.8097952266799876e-05, "loss": 0.4297, "step": 1840 }, { "epoch": 0.8545034642032333, "grad_norm": 3.403167963027954, "learning_rate": 4.805921126294129e-05, "loss": 0.4028, "step": 1850 }, { "epoch": 0.859122401847575, "grad_norm": 1.5918769836425781, "learning_rate": 4.802009561161396e-05, "loss": 0.3982, "step": 1860 }, { "epoch": 0.8637413394919169, "grad_norm": 2.220611333847046, "learning_rate": 4.798060594833743e-05, "loss": 0.4213, "step": 1870 }, { "epoch": 0.8683602771362586, "grad_norm": 1.634158968925476, "learning_rate": 4.794074291470791e-05, "loss": 0.4085, "step": 1880 }, { "epoch": 0.8729792147806005, "grad_norm": 2.6168339252471924, "learning_rate": 4.790050715838783e-05, "loss": 0.437, "step": 1890 }, { "epoch": 0.8775981524249422, "grad_norm": 2.0392565727233887, "learning_rate": 4.7859899333095296e-05, "loss": 0.4407, "step": 1900 }, { "epoch": 0.8822170900692841, "grad_norm": 2.446300506591797, "learning_rate": 4.7818920098593516e-05, "loss": 0.4415, "step": 1910 }, { "epoch": 0.8868360277136259, "grad_norm": 2.7988600730895996, "learning_rate": 4.777757012068004e-05, "loss": 0.433, "step": 1920 }, { "epoch": 0.8914549653579676, "grad_norm": 1.9571830034255981, "learning_rate": 4.773585007117597e-05, "loss": 0.3957, "step": 1930 }, { "epoch": 0.8960739030023095, "grad_norm": 3.4647884368896484, "learning_rate": 4.7693760627915015e-05, "loss": 0.4442, "step": 1940 }, { "epoch": 0.9006928406466512, "grad_norm": 2.8123703002929688, "learning_rate": 4.765130247473252e-05, "loss": 0.502, "step": 1950 }, { "epoch": 0.9053117782909931, "grad_norm": 2.4884793758392334, "learning_rate": 4.760847630145431e-05, "loss": 0.4532, "step": 1960 }, { "epoch": 0.9099307159353349, "grad_norm": 2.372985601425171, "learning_rate": 4.756528280388551e-05, "loss": 0.3951, "step": 1970 }, { "epoch": 0.9145496535796767, "grad_norm": 2.322315216064453, "learning_rate": 4.752172268379923e-05, "loss": 0.4442, "step": 1980 }, { "epoch": 0.9191685912240185, "grad_norm": 2.875863552093506, "learning_rate": 4.7477796648925186e-05, "loss": 0.4512, "step": 1990 }, { "epoch": 0.9237875288683602, "grad_norm": 2.0720949172973633, "learning_rate": 4.743350541293817e-05, "loss": 0.4076, "step": 2000 }, { "epoch": 0.9284064665127021, "grad_norm": 2.1072168350219727, "learning_rate": 4.738884969544646e-05, "loss": 0.3686, "step": 2010 }, { "epoch": 0.9330254041570438, "grad_norm": 2.536849021911621, "learning_rate": 4.734383022198013e-05, "loss": 0.3822, "step": 2020 }, { "epoch": 0.9376443418013857, "grad_norm": 2.638981580734253, "learning_rate": 4.72984477239793e-05, "loss": 0.3934, "step": 2030 }, { "epoch": 0.9422632794457275, "grad_norm": 2.287445545196533, "learning_rate": 4.725270293878218e-05, "loss": 0.4234, "step": 2040 }, { "epoch": 0.9468822170900693, "grad_norm": 3.737877130508423, "learning_rate": 4.720659660961316e-05, "loss": 0.3855, "step": 2050 }, { "epoch": 0.9515011547344111, "grad_norm": 1.3333017826080322, "learning_rate": 4.7160129485570706e-05, "loss": 0.4159, "step": 2060 }, { "epoch": 0.9561200923787528, "grad_norm": 3.8679983615875244, "learning_rate": 4.711330232161515e-05, "loss": 0.3882, "step": 2070 }, { "epoch": 0.9607390300230947, "grad_norm": 2.0616493225097656, "learning_rate": 4.706611587855651e-05, "loss": 0.4304, "step": 2080 }, { "epoch": 0.9653579676674365, "grad_norm": 1.910409688949585, "learning_rate": 4.7018570923042054e-05, "loss": 0.4648, "step": 2090 }, { "epoch": 0.9699769053117783, "grad_norm": 2.010974645614624, "learning_rate": 4.697066822754388e-05, "loss": 0.407, "step": 2100 }, { "epoch": 0.9745958429561201, "grad_norm": 2.0885708332061768, "learning_rate": 4.692240857034634e-05, "loss": 0.4084, "step": 2110 }, { "epoch": 0.9792147806004619, "grad_norm": 2.3431713581085205, "learning_rate": 4.6873792735533436e-05, "loss": 0.436, "step": 2120 }, { "epoch": 0.9838337182448037, "grad_norm": 2.349169969558716, "learning_rate": 4.682482151297605e-05, "loss": 0.4102, "step": 2130 }, { "epoch": 0.9884526558891455, "grad_norm": 2.2386903762817383, "learning_rate": 4.6775495698319114e-05, "loss": 0.4126, "step": 2140 }, { "epoch": 0.9930715935334873, "grad_norm": 1.9783356189727783, "learning_rate": 4.672581609296868e-05, "loss": 0.4056, "step": 2150 }, { "epoch": 0.9976905311778291, "grad_norm": 1.545580506324768, "learning_rate": 4.667578350407891e-05, "loss": 0.4159, "step": 2160 }, { "epoch": 1.002309468822171, "grad_norm": 2.3541977405548096, "learning_rate": 4.662539874453896e-05, "loss": 0.3425, "step": 2170 }, { "epoch": 1.0069284064665127, "grad_norm": 1.4054622650146484, "learning_rate": 4.657466263295978e-05, "loss": 0.2923, "step": 2180 }, { "epoch": 1.0115473441108545, "grad_norm": 2.2558600902557373, "learning_rate": 4.652357599366078e-05, "loss": 0.3432, "step": 2190 }, { "epoch": 1.0161662817551964, "grad_norm": 2.1105244159698486, "learning_rate": 4.6472139656656504e-05, "loss": 0.3093, "step": 2200 }, { "epoch": 1.0207852193995381, "grad_norm": 1.7107679843902588, "learning_rate": 4.642035445764305e-05, "loss": 0.2854, "step": 2210 }, { "epoch": 1.0254041570438799, "grad_norm": 2.075529098510742, "learning_rate": 4.636822123798458e-05, "loss": 0.3232, "step": 2220 }, { "epoch": 1.0300230946882216, "grad_norm": 2.467179536819458, "learning_rate": 4.6315740844699606e-05, "loss": 0.3597, "step": 2230 }, { "epoch": 1.0346420323325636, "grad_norm": 1.628585934638977, "learning_rate": 4.626291413044723e-05, "loss": 0.3165, "step": 2240 }, { "epoch": 1.0392609699769053, "grad_norm": 1.6538641452789307, "learning_rate": 4.620974195351331e-05, "loss": 0.3332, "step": 2250 }, { "epoch": 1.043879907621247, "grad_norm": 1.2917189598083496, "learning_rate": 4.615622517779648e-05, "loss": 0.3207, "step": 2260 }, { "epoch": 1.048498845265589, "grad_norm": 1.6541030406951904, "learning_rate": 4.6102364672794186e-05, "loss": 0.3206, "step": 2270 }, { "epoch": 1.0531177829099307, "grad_norm": 2.9960944652557373, "learning_rate": 4.6048161313588454e-05, "loss": 0.3283, "step": 2280 }, { "epoch": 1.0577367205542725, "grad_norm": 1.576786994934082, "learning_rate": 4.599361598083175e-05, "loss": 0.3108, "step": 2290 }, { "epoch": 1.0623556581986142, "grad_norm": 2.9151947498321533, "learning_rate": 4.593872956073267e-05, "loss": 0.3134, "step": 2300 }, { "epoch": 1.0669745958429562, "grad_norm": 1.6089911460876465, "learning_rate": 4.588350294504149e-05, "loss": 0.3059, "step": 2310 }, { "epoch": 1.071593533487298, "grad_norm": 2.043606996536255, "learning_rate": 4.582793703103574e-05, "loss": 0.3063, "step": 2320 }, { "epoch": 1.0762124711316396, "grad_norm": 1.3332914113998413, "learning_rate": 4.577203272150557e-05, "loss": 0.3358, "step": 2330 }, { "epoch": 1.0808314087759816, "grad_norm": 1.6624664068222046, "learning_rate": 4.571579092473911e-05, "loss": 0.327, "step": 2340 }, { "epoch": 1.0854503464203233, "grad_norm": 1.5694808959960938, "learning_rate": 4.565921255450773e-05, "loss": 0.3128, "step": 2350 }, { "epoch": 1.090069284064665, "grad_norm": 2.037529468536377, "learning_rate": 4.5602298530051165e-05, "loss": 0.3295, "step": 2360 }, { "epoch": 1.0946882217090068, "grad_norm": 2.3830647468566895, "learning_rate": 4.5545049776062577e-05, "loss": 0.3218, "step": 2370 }, { "epoch": 1.0993071593533488, "grad_norm": 1.4938024282455444, "learning_rate": 4.548746722267356e-05, "loss": 0.3154, "step": 2380 }, { "epoch": 1.1039260969976905, "grad_norm": 2.7618491649627686, "learning_rate": 4.542955180543901e-05, "loss": 0.2857, "step": 2390 }, { "epoch": 1.1085450346420322, "grad_norm": 1.6438803672790527, "learning_rate": 4.53713044653219e-05, "loss": 0.2997, "step": 2400 }, { "epoch": 1.1131639722863742, "grad_norm": 1.8261016607284546, "learning_rate": 4.531272614867806e-05, "loss": 0.3157, "step": 2410 }, { "epoch": 1.117782909930716, "grad_norm": 1.5871988534927368, "learning_rate": 4.525381780724073e-05, "loss": 0.3208, "step": 2420 }, { "epoch": 1.1224018475750577, "grad_norm": 2.379218339920044, "learning_rate": 4.519458039810515e-05, "loss": 0.2979, "step": 2430 }, { "epoch": 1.1270207852193996, "grad_norm": 1.5023610591888428, "learning_rate": 4.513501488371294e-05, "loss": 0.2979, "step": 2440 }, { "epoch": 1.1316397228637414, "grad_norm": 1.8525944948196411, "learning_rate": 4.5075122231836575e-05, "loss": 0.3316, "step": 2450 }, { "epoch": 1.136258660508083, "grad_norm": 2.108273983001709, "learning_rate": 4.501490341556354e-05, "loss": 0.3246, "step": 2460 }, { "epoch": 1.140877598152425, "grad_norm": 1.5220661163330078, "learning_rate": 4.495435941328062e-05, "loss": 0.3256, "step": 2470 }, { "epoch": 1.1454965357967668, "grad_norm": 1.5954303741455078, "learning_rate": 4.489349120865792e-05, "loss": 0.3325, "step": 2480 }, { "epoch": 1.1501154734411085, "grad_norm": 2.012314558029175, "learning_rate": 4.483229979063295e-05, "loss": 0.328, "step": 2490 }, { "epoch": 1.1547344110854503, "grad_norm": 2.3194642066955566, "learning_rate": 4.4770786153394526e-05, "loss": 0.2955, "step": 2500 }, { "epoch": 1.1593533487297922, "grad_norm": 2.1321589946746826, "learning_rate": 4.470895129636662e-05, "loss": 0.3145, "step": 2510 }, { "epoch": 1.163972286374134, "grad_norm": 1.6388169527053833, "learning_rate": 4.464679622419211e-05, "loss": 0.324, "step": 2520 }, { "epoch": 1.1685912240184757, "grad_norm": 1.7595680952072144, "learning_rate": 4.45843219467165e-05, "loss": 0.3178, "step": 2530 }, { "epoch": 1.1732101616628174, "grad_norm": 1.8043133020401, "learning_rate": 4.452152947897146e-05, "loss": 0.2641, "step": 2540 }, { "epoch": 1.1778290993071594, "grad_norm": 2.0495808124542236, "learning_rate": 4.445841984115836e-05, "loss": 0.3144, "step": 2550 }, { "epoch": 1.1824480369515011, "grad_norm": 2.4559502601623535, "learning_rate": 4.4394994058631724e-05, "loss": 0.2987, "step": 2560 }, { "epoch": 1.1870669745958429, "grad_norm": 1.9398882389068604, "learning_rate": 4.433125316188249e-05, "loss": 0.314, "step": 2570 }, { "epoch": 1.1916859122401848, "grad_norm": 2.5720202922821045, "learning_rate": 4.426719818652137e-05, "loss": 0.3346, "step": 2580 }, { "epoch": 1.1963048498845266, "grad_norm": 2.9271321296691895, "learning_rate": 4.4202830173261936e-05, "loss": 0.3118, "step": 2590 }, { "epoch": 1.2009237875288683, "grad_norm": 4.06657600402832, "learning_rate": 4.413815016790376e-05, "loss": 0.3118, "step": 2600 }, { "epoch": 1.2055427251732103, "grad_norm": 1.627180814743042, "learning_rate": 4.4073159221315396e-05, "loss": 0.3239, "step": 2610 }, { "epoch": 1.210161662817552, "grad_norm": 3.904036283493042, "learning_rate": 4.4007858389417354e-05, "loss": 0.3295, "step": 2620 }, { "epoch": 1.2147806004618937, "grad_norm": 1.2671165466308594, "learning_rate": 4.3942248733164884e-05, "loss": 0.285, "step": 2630 }, { "epoch": 1.2193995381062355, "grad_norm": 2.1351537704467773, "learning_rate": 4.3876331318530755e-05, "loss": 0.315, "step": 2640 }, { "epoch": 1.2240184757505774, "grad_norm": 2.152552366256714, "learning_rate": 4.381010721648798e-05, "loss": 0.3065, "step": 2650 }, { "epoch": 1.2286374133949192, "grad_norm": 2.0803706645965576, "learning_rate": 4.374357750299236e-05, "loss": 0.3419, "step": 2660 }, { "epoch": 1.233256351039261, "grad_norm": 1.8164416551589966, "learning_rate": 4.3676743258965015e-05, "loss": 0.3044, "step": 2670 }, { "epoch": 1.2378752886836029, "grad_norm": 1.7581324577331543, "learning_rate": 4.3609605570274856e-05, "loss": 0.3248, "step": 2680 }, { "epoch": 1.2424942263279446, "grad_norm": 2.031179904937744, "learning_rate": 4.3542165527720915e-05, "loss": 0.3262, "step": 2690 }, { "epoch": 1.2471131639722863, "grad_norm": 1.826240062713623, "learning_rate": 4.347442422701459e-05, "loss": 0.2911, "step": 2700 }, { "epoch": 1.251732101616628, "grad_norm": 1.4430904388427734, "learning_rate": 4.3406382768761935e-05, "loss": 0.305, "step": 2710 }, { "epoch": 1.25635103926097, "grad_norm": 1.7261760234832764, "learning_rate": 4.333804225844567e-05, "loss": 0.3197, "step": 2720 }, { "epoch": 1.2609699769053118, "grad_norm": 1.8625311851501465, "learning_rate": 4.326940380640731e-05, "loss": 0.3265, "step": 2730 }, { "epoch": 1.2655889145496535, "grad_norm": 2.4488320350646973, "learning_rate": 4.3200468527829055e-05, "loss": 0.294, "step": 2740 }, { "epoch": 1.2702078521939955, "grad_norm": 1.8369277715682983, "learning_rate": 4.313123754271574e-05, "loss": 0.3141, "step": 2750 }, { "epoch": 1.2748267898383372, "grad_norm": 1.7010807991027832, "learning_rate": 4.3061711975876564e-05, "loss": 0.3119, "step": 2760 }, { "epoch": 1.279445727482679, "grad_norm": 1.5624935626983643, "learning_rate": 4.2991892956906865e-05, "loss": 0.3199, "step": 2770 }, { "epoch": 1.2840646651270209, "grad_norm": 2.6501541137695312, "learning_rate": 4.2921781620169776e-05, "loss": 0.2817, "step": 2780 }, { "epoch": 1.2886836027713626, "grad_norm": 1.5064769983291626, "learning_rate": 4.285137910477774e-05, "loss": 0.3012, "step": 2790 }, { "epoch": 1.2933025404157044, "grad_norm": 1.9986552000045776, "learning_rate": 4.278068655457408e-05, "loss": 0.2705, "step": 2800 }, { "epoch": 1.2979214780600463, "grad_norm": 1.8197659254074097, "learning_rate": 4.27097051181143e-05, "loss": 0.2814, "step": 2810 }, { "epoch": 1.302540415704388, "grad_norm": 1.5221188068389893, "learning_rate": 4.2638435948647564e-05, "loss": 0.3154, "step": 2820 }, { "epoch": 1.3071593533487298, "grad_norm": 1.5869982242584229, "learning_rate": 4.256688020409786e-05, "loss": 0.2716, "step": 2830 }, { "epoch": 1.3117782909930715, "grad_norm": 2.0754973888397217, "learning_rate": 4.249503904704522e-05, "loss": 0.2901, "step": 2840 }, { "epoch": 1.3163972286374133, "grad_norm": 2.163522243499756, "learning_rate": 4.242291364470682e-05, "loss": 0.2968, "step": 2850 }, { "epoch": 1.3210161662817552, "grad_norm": 3.169379472732544, "learning_rate": 4.235050516891804e-05, "loss": 0.337, "step": 2860 }, { "epoch": 1.325635103926097, "grad_norm": 2.4248273372650146, "learning_rate": 4.227781479611341e-05, "loss": 0.3052, "step": 2870 }, { "epoch": 1.3302540415704387, "grad_norm": 2.0661935806274414, "learning_rate": 4.220484370730746e-05, "loss": 0.2999, "step": 2880 }, { "epoch": 1.3348729792147807, "grad_norm": 2.3294215202331543, "learning_rate": 4.213159308807563e-05, "loss": 0.3077, "step": 2890 }, { "epoch": 1.3394919168591224, "grad_norm": 1.8532743453979492, "learning_rate": 4.205806412853488e-05, "loss": 0.3034, "step": 2900 }, { "epoch": 1.3441108545034641, "grad_norm": 1.987816333770752, "learning_rate": 4.198425802332446e-05, "loss": 0.3049, "step": 2910 }, { "epoch": 1.348729792147806, "grad_norm": 2.121181011199951, "learning_rate": 4.191017597158645e-05, "loss": 0.2842, "step": 2920 }, { "epoch": 1.3533487297921478, "grad_norm": 1.72597336769104, "learning_rate": 4.183581917694627e-05, "loss": 0.2924, "step": 2930 }, { "epoch": 1.3579676674364896, "grad_norm": 2.3341033458709717, "learning_rate": 4.1761188847493174e-05, "loss": 0.3303, "step": 2940 }, { "epoch": 1.3625866050808315, "grad_norm": 1.3130851984024048, "learning_rate": 4.168628619576056e-05, "loss": 0.3022, "step": 2950 }, { "epoch": 1.3672055427251733, "grad_norm": 1.6701748371124268, "learning_rate": 4.161111243870631e-05, "loss": 0.2885, "step": 2960 }, { "epoch": 1.371824480369515, "grad_norm": 1.4572288990020752, "learning_rate": 4.1535668797693e-05, "loss": 0.3114, "step": 2970 }, { "epoch": 1.376443418013857, "grad_norm": 1.6978940963745117, "learning_rate": 4.145995649846808e-05, "loss": 0.2594, "step": 2980 }, { "epoch": 1.3810623556581987, "grad_norm": 1.2742643356323242, "learning_rate": 4.138397677114393e-05, "loss": 0.3137, "step": 2990 }, { "epoch": 1.3856812933025404, "grad_norm": 2.4312751293182373, "learning_rate": 4.1307730850177865e-05, "loss": 0.2967, "step": 3000 }, { "epoch": 1.3903002309468822, "grad_norm": 2.715585708618164, "learning_rate": 4.123121997435215e-05, "loss": 0.3043, "step": 3010 }, { "epoch": 1.394919168591224, "grad_norm": 1.99354887008667, "learning_rate": 4.115444538675378e-05, "loss": 0.2914, "step": 3020 }, { "epoch": 1.3995381062355658, "grad_norm": 1.861504316329956, "learning_rate": 4.1077408334754335e-05, "loss": 0.2637, "step": 3030 }, { "epoch": 1.4041570438799076, "grad_norm": 1.8581842184066772, "learning_rate": 4.1000110069989724e-05, "loss": 0.2907, "step": 3040 }, { "epoch": 1.4087759815242493, "grad_norm": 1.6948480606079102, "learning_rate": 4.092255184833981e-05, "loss": 0.3158, "step": 3050 }, { "epoch": 1.4133949191685913, "grad_norm": 2.080018997192383, "learning_rate": 4.0844734929908025e-05, "loss": 0.3259, "step": 3060 }, { "epoch": 1.418013856812933, "grad_norm": 1.1076098680496216, "learning_rate": 4.076666057900091e-05, "loss": 0.2839, "step": 3070 }, { "epoch": 1.4226327944572748, "grad_norm": 2.909213066101074, "learning_rate": 4.068833006410757e-05, "loss": 0.2865, "step": 3080 }, { "epoch": 1.4272517321016167, "grad_norm": 1.6407644748687744, "learning_rate": 4.0609744657879024e-05, "loss": 0.2718, "step": 3090 }, { "epoch": 1.4318706697459584, "grad_norm": 2.367949962615967, "learning_rate": 4.0530905637107584e-05, "loss": 0.3163, "step": 3100 }, { "epoch": 1.4364896073903002, "grad_norm": 1.6912730932235718, "learning_rate": 4.0451814282706085e-05, "loss": 0.3377, "step": 3110 }, { "epoch": 1.4411085450346421, "grad_norm": 1.321198582649231, "learning_rate": 4.037247187968706e-05, "loss": 0.2846, "step": 3120 }, { "epoch": 1.4457274826789839, "grad_norm": 2.0895841121673584, "learning_rate": 4.02928797171419e-05, "loss": 0.3111, "step": 3130 }, { "epoch": 1.4503464203233256, "grad_norm": 1.6102547645568848, "learning_rate": 4.021303908821987e-05, "loss": 0.2987, "step": 3140 }, { "epoch": 1.4549653579676676, "grad_norm": 1.1567573547363281, "learning_rate": 4.013295129010712e-05, "loss": 0.3045, "step": 3150 }, { "epoch": 1.4595842956120093, "grad_norm": 3.8533406257629395, "learning_rate": 4.005261762400562e-05, "loss": 0.3208, "step": 3160 }, { "epoch": 1.464203233256351, "grad_norm": 2.1979851722717285, "learning_rate": 3.997203939511198e-05, "loss": 0.2706, "step": 3170 }, { "epoch": 1.4688221709006928, "grad_norm": 1.7719027996063232, "learning_rate": 3.989121791259629e-05, "loss": 0.2948, "step": 3180 }, { "epoch": 1.4734411085450345, "grad_norm": 2.193924903869629, "learning_rate": 3.98101544895808e-05, "loss": 0.2977, "step": 3190 }, { "epoch": 1.4780600461893765, "grad_norm": 1.6634687185287476, "learning_rate": 3.972885044311867e-05, "loss": 0.2933, "step": 3200 }, { "epoch": 1.4826789838337182, "grad_norm": 1.2648128271102905, "learning_rate": 3.964730709417245e-05, "loss": 0.2989, "step": 3210 }, { "epoch": 1.48729792147806, "grad_norm": 8.130200386047363, "learning_rate": 3.956552576759272e-05, "loss": 0.3293, "step": 3220 }, { "epoch": 1.491916859122402, "grad_norm": 2.254474639892578, "learning_rate": 3.948350779209653e-05, "loss": 0.3134, "step": 3230 }, { "epoch": 1.4965357967667436, "grad_norm": 1.8100476264953613, "learning_rate": 3.940125450024581e-05, "loss": 0.3405, "step": 3240 }, { "epoch": 1.5011547344110854, "grad_norm": 2.5194456577301025, "learning_rate": 3.931876722842569e-05, "loss": 0.3073, "step": 3250 }, { "epoch": 1.5057736720554273, "grad_norm": 2.842329502105713, "learning_rate": 3.9236047316822866e-05, "loss": 0.2643, "step": 3260 }, { "epoch": 1.510392609699769, "grad_norm": 2.350539445877075, "learning_rate": 3.9153096109403736e-05, "loss": 0.2983, "step": 3270 }, { "epoch": 1.5150115473441108, "grad_norm": 2.8748178482055664, "learning_rate": 3.906991495389263e-05, "loss": 0.2785, "step": 3280 }, { "epoch": 1.5196304849884528, "grad_norm": 2.3582661151885986, "learning_rate": 3.898650520174989e-05, "loss": 0.2953, "step": 3290 }, { "epoch": 1.5242494226327945, "grad_norm": 2.257141590118408, "learning_rate": 3.890286820814989e-05, "loss": 0.278, "step": 3300 }, { "epoch": 1.5288683602771362, "grad_norm": 3.344249963760376, "learning_rate": 3.881900533195906e-05, "loss": 0.2853, "step": 3310 }, { "epoch": 1.5334872979214782, "grad_norm": 2.0517385005950928, "learning_rate": 3.873491793571378e-05, "loss": 0.2794, "step": 3320 }, { "epoch": 1.5381062355658197, "grad_norm": 2.145541191101074, "learning_rate": 3.8650607385598256e-05, "loss": 0.3133, "step": 3330 }, { "epoch": 1.5427251732101617, "grad_norm": 1.6390986442565918, "learning_rate": 3.856607505142232e-05, "loss": 0.2763, "step": 3340 }, { "epoch": 1.5473441108545036, "grad_norm": 2.163872241973877, "learning_rate": 3.8481322306599154e-05, "loss": 0.2951, "step": 3350 }, { "epoch": 1.5519630484988451, "grad_norm": 1.493821382522583, "learning_rate": 3.839635052812302e-05, "loss": 0.2754, "step": 3360 }, { "epoch": 1.556581986143187, "grad_norm": 1.9270718097686768, "learning_rate": 3.831116109654684e-05, "loss": 0.2972, "step": 3370 }, { "epoch": 1.5612009237875288, "grad_norm": 2.00677227973938, "learning_rate": 3.822575539595981e-05, "loss": 0.2637, "step": 3380 }, { "epoch": 1.5658198614318706, "grad_norm": 3.3901729583740234, "learning_rate": 3.8140134813964866e-05, "loss": 0.2946, "step": 3390 }, { "epoch": 1.5704387990762125, "grad_norm": 2.659478187561035, "learning_rate": 3.8054300741656186e-05, "loss": 0.33, "step": 3400 }, { "epoch": 1.5750577367205543, "grad_norm": 2.5138628482818604, "learning_rate": 3.796825457359655e-05, "loss": 0.2866, "step": 3410 }, { "epoch": 1.579676674364896, "grad_norm": 1.9975327253341675, "learning_rate": 3.7881997707794716e-05, "loss": 0.3171, "step": 3420 }, { "epoch": 1.584295612009238, "grad_norm": 1.2960349321365356, "learning_rate": 3.779553154568266e-05, "loss": 0.2952, "step": 3430 }, { "epoch": 1.5889145496535797, "grad_norm": 1.4498865604400635, "learning_rate": 3.7708857492092874e-05, "loss": 0.2759, "step": 3440 }, { "epoch": 1.5935334872979214, "grad_norm": 1.7237732410430908, "learning_rate": 3.762197695523547e-05, "loss": 0.2781, "step": 3450 }, { "epoch": 1.5981524249422634, "grad_norm": 1.2863229513168335, "learning_rate": 3.7534891346675367e-05, "loss": 0.2587, "step": 3460 }, { "epoch": 1.6027713625866051, "grad_norm": 2.125469446182251, "learning_rate": 3.744760208130928e-05, "loss": 0.3124, "step": 3470 }, { "epoch": 1.6073903002309469, "grad_norm": 1.4202874898910522, "learning_rate": 3.73601105773428e-05, "loss": 0.298, "step": 3480 }, { "epoch": 1.6120092378752888, "grad_norm": 2.05185604095459, "learning_rate": 3.7272418256267347e-05, "loss": 0.2934, "step": 3490 }, { "epoch": 1.6166281755196303, "grad_norm": 1.3896102905273438, "learning_rate": 3.7184526542837016e-05, "loss": 0.2804, "step": 3500 }, { "epoch": 1.6212471131639723, "grad_norm": 2.8163557052612305, "learning_rate": 3.70964368650455e-05, "loss": 0.2784, "step": 3510 }, { "epoch": 1.625866050808314, "grad_norm": 1.828988790512085, "learning_rate": 3.700815065410284e-05, "loss": 0.2792, "step": 3520 }, { "epoch": 1.6304849884526558, "grad_norm": 1.8689284324645996, "learning_rate": 3.691966934441219e-05, "loss": 0.2988, "step": 3530 }, { "epoch": 1.6351039260969977, "grad_norm": 2.0049326419830322, "learning_rate": 3.683099437354652e-05, "loss": 0.3078, "step": 3540 }, { "epoch": 1.6397228637413395, "grad_norm": 1.4969823360443115, "learning_rate": 3.674212718222524e-05, "loss": 0.3172, "step": 3550 }, { "epoch": 1.6443418013856812, "grad_norm": 1.2747870683670044, "learning_rate": 3.665306921429082e-05, "loss": 0.2628, "step": 3560 }, { "epoch": 1.6489607390300232, "grad_norm": 1.9167592525482178, "learning_rate": 3.65638219166853e-05, "loss": 0.2734, "step": 3570 }, { "epoch": 1.653579676674365, "grad_norm": 1.5603243112564087, "learning_rate": 3.647438673942679e-05, "loss": 0.2884, "step": 3580 }, { "epoch": 1.6581986143187066, "grad_norm": 1.914704442024231, "learning_rate": 3.638476513558593e-05, "loss": 0.3117, "step": 3590 }, { "epoch": 1.6628175519630486, "grad_norm": 1.5785443782806396, "learning_rate": 3.629495856126227e-05, "loss": 0.296, "step": 3600 }, { "epoch": 1.6674364896073903, "grad_norm": 2.8318498134613037, "learning_rate": 3.62049684755606e-05, "loss": 0.3182, "step": 3610 }, { "epoch": 1.672055427251732, "grad_norm": 1.5652984380722046, "learning_rate": 3.611479634056726e-05, "loss": 0.2857, "step": 3620 }, { "epoch": 1.676674364896074, "grad_norm": 1.944756269454956, "learning_rate": 3.6024443621326386e-05, "loss": 0.2808, "step": 3630 }, { "epoch": 1.6812933025404158, "grad_norm": 1.403517723083496, "learning_rate": 3.5933911785816096e-05, "loss": 0.2801, "step": 3640 }, { "epoch": 1.6859122401847575, "grad_norm": 1.477249264717102, "learning_rate": 3.5843202304924646e-05, "loss": 0.2881, "step": 3650 }, { "epoch": 1.6905311778290995, "grad_norm": 1.5196659564971924, "learning_rate": 3.575231665242652e-05, "loss": 0.287, "step": 3660 }, { "epoch": 1.695150115473441, "grad_norm": 1.6413066387176514, "learning_rate": 3.5661256304958515e-05, "loss": 0.2941, "step": 3670 }, { "epoch": 1.699769053117783, "grad_norm": 2.7491331100463867, "learning_rate": 3.5570022741995726e-05, "loss": 0.2754, "step": 3680 }, { "epoch": 1.7043879907621247, "grad_norm": 1.9118013381958008, "learning_rate": 3.547861744582751e-05, "loss": 0.2977, "step": 3690 }, { "epoch": 1.7090069284064664, "grad_norm": 2.301297664642334, "learning_rate": 3.538704190153338e-05, "loss": 0.3165, "step": 3700 }, { "epoch": 1.7136258660508084, "grad_norm": 1.9769275188446045, "learning_rate": 3.529529759695897e-05, "loss": 0.2717, "step": 3710 }, { "epoch": 1.71824480369515, "grad_norm": 1.8014106750488281, "learning_rate": 3.5203386022691725e-05, "loss": 0.2878, "step": 3720 }, { "epoch": 1.7228637413394918, "grad_norm": 1.4981132745742798, "learning_rate": 3.511130867203679e-05, "loss": 0.3015, "step": 3730 }, { "epoch": 1.7274826789838338, "grad_norm": 2.6058621406555176, "learning_rate": 3.5019067040992716e-05, "loss": 0.273, "step": 3740 }, { "epoch": 1.7321016166281755, "grad_norm": 1.584773302078247, "learning_rate": 3.492666262822712e-05, "loss": 0.2934, "step": 3750 }, { "epoch": 1.7367205542725173, "grad_norm": 1.560206651687622, "learning_rate": 3.4834096935052384e-05, "loss": 0.2953, "step": 3760 }, { "epoch": 1.7413394919168592, "grad_norm": 1.7597191333770752, "learning_rate": 3.4741371465401257e-05, "loss": 0.2823, "step": 3770 }, { "epoch": 1.745958429561201, "grad_norm": 2.0354883670806885, "learning_rate": 3.464848772580238e-05, "loss": 0.2891, "step": 3780 }, { "epoch": 1.7505773672055427, "grad_norm": 1.609017014503479, "learning_rate": 3.4555447225355846e-05, "loss": 0.3128, "step": 3790 }, { "epoch": 1.7551963048498846, "grad_norm": 1.5989829301834106, "learning_rate": 3.446225147570868e-05, "loss": 0.2657, "step": 3800 }, { "epoch": 1.7598152424942262, "grad_norm": 1.2893913984298706, "learning_rate": 3.4368901991030274e-05, "loss": 0.3069, "step": 3810 }, { "epoch": 1.7644341801385681, "grad_norm": 2.286530017852783, "learning_rate": 3.427540028798777e-05, "loss": 0.2777, "step": 3820 }, { "epoch": 1.76905311778291, "grad_norm": 1.5108604431152344, "learning_rate": 3.418174788572142e-05, "loss": 0.2766, "step": 3830 }, { "epoch": 1.7736720554272516, "grad_norm": 2.1151463985443115, "learning_rate": 3.408794630581994e-05, "loss": 0.2768, "step": 3840 }, { "epoch": 1.7782909930715936, "grad_norm": 1.4819116592407227, "learning_rate": 3.399399707229577e-05, "loss": 0.2866, "step": 3850 }, { "epoch": 1.7829099307159353, "grad_norm": 1.969902515411377, "learning_rate": 3.389990171156028e-05, "loss": 0.2824, "step": 3860 }, { "epoch": 1.787528868360277, "grad_norm": 2.0315933227539062, "learning_rate": 3.3805661752399e-05, "loss": 0.264, "step": 3870 }, { "epoch": 1.792147806004619, "grad_norm": 1.282948613166809, "learning_rate": 3.37112787259468e-05, "loss": 0.2864, "step": 3880 }, { "epoch": 1.7967667436489607, "grad_norm": 2.9602625370025635, "learning_rate": 3.3616754165662975e-05, "loss": 0.2957, "step": 3890 }, { "epoch": 1.8013856812933025, "grad_norm": 1.5547012090682983, "learning_rate": 3.352208960730636e-05, "loss": 0.2679, "step": 3900 }, { "epoch": 1.8060046189376444, "grad_norm": 2.2637956142425537, "learning_rate": 3.342728658891034e-05, "loss": 0.3021, "step": 3910 }, { "epoch": 1.8106235565819861, "grad_norm": 1.8979109525680542, "learning_rate": 3.333234665075792e-05, "loss": 0.2647, "step": 3920 }, { "epoch": 1.8152424942263279, "grad_norm": 1.8908520936965942, "learning_rate": 3.323727133535665e-05, "loss": 0.3233, "step": 3930 }, { "epoch": 1.8198614318706698, "grad_norm": 1.8832924365997314, "learning_rate": 3.314206218741359e-05, "loss": 0.2596, "step": 3940 }, { "epoch": 1.8244803695150116, "grad_norm": 2.1820366382598877, "learning_rate": 3.304672075381017e-05, "loss": 0.2887, "step": 3950 }, { "epoch": 1.8290993071593533, "grad_norm": 3.660722017288208, "learning_rate": 3.295124858357714e-05, "loss": 0.2725, "step": 3960 }, { "epoch": 1.8337182448036953, "grad_norm": 1.5924043655395508, "learning_rate": 3.285564722786932e-05, "loss": 0.3009, "step": 3970 }, { "epoch": 1.8383371824480368, "grad_norm": 1.8681361675262451, "learning_rate": 3.2759918239940446e-05, "loss": 0.2574, "step": 3980 }, { "epoch": 1.8429561200923787, "grad_norm": 1.568429946899414, "learning_rate": 3.2664063175117906e-05, "loss": 0.2773, "step": 3990 }, { "epoch": 1.8475750577367207, "grad_norm": 2.8081066608428955, "learning_rate": 3.25680835907775e-05, "loss": 0.2487, "step": 4000 }, { "epoch": 1.8521939953810622, "grad_norm": 2.6181676387786865, "learning_rate": 3.24719810463181e-05, "loss": 0.2721, "step": 4010 }, { "epoch": 1.8568129330254042, "grad_norm": 1.3236477375030518, "learning_rate": 3.237575710313636e-05, "loss": 0.2623, "step": 4020 }, { "epoch": 1.861431870669746, "grad_norm": 1.6242995262145996, "learning_rate": 3.227941332460132e-05, "loss": 0.2444, "step": 4030 }, { "epoch": 1.8660508083140877, "grad_norm": 1.3549182415008545, "learning_rate": 3.2182951276028975e-05, "loss": 0.3071, "step": 4040 }, { "epoch": 1.8706697459584296, "grad_norm": 1.4465357065200806, "learning_rate": 3.2086372524656905e-05, "loss": 0.2471, "step": 4050 }, { "epoch": 1.8752886836027713, "grad_norm": 2.5202062129974365, "learning_rate": 3.1989678639618786e-05, "loss": 0.2951, "step": 4060 }, { "epoch": 1.879907621247113, "grad_norm": 1.2231857776641846, "learning_rate": 3.1892871191918884e-05, "loss": 0.2643, "step": 4070 }, { "epoch": 1.884526558891455, "grad_norm": 2.562093496322632, "learning_rate": 3.1795951754406524e-05, "loss": 0.2774, "step": 4080 }, { "epoch": 1.8891454965357968, "grad_norm": 1.4063376188278198, "learning_rate": 3.169892190175059e-05, "loss": 0.3056, "step": 4090 }, { "epoch": 1.8937644341801385, "grad_norm": 2.15189528465271, "learning_rate": 3.160178321041387e-05, "loss": 0.2803, "step": 4100 }, { "epoch": 1.8983833718244805, "grad_norm": 1.3879120349884033, "learning_rate": 3.150453725862749e-05, "loss": 0.2704, "step": 4110 }, { "epoch": 1.9030023094688222, "grad_norm": 2.075014591217041, "learning_rate": 3.1407185626365224e-05, "loss": 0.2924, "step": 4120 }, { "epoch": 1.907621247113164, "grad_norm": 1.839989185333252, "learning_rate": 3.130972989531792e-05, "loss": 0.2686, "step": 4130 }, { "epoch": 1.912240184757506, "grad_norm": 1.0090025663375854, "learning_rate": 3.1212171648867685e-05, "loss": 0.3036, "step": 4140 }, { "epoch": 1.9168591224018474, "grad_norm": 2.8527584075927734, "learning_rate": 3.111451247206223e-05, "loss": 0.2907, "step": 4150 }, { "epoch": 1.9214780600461894, "grad_norm": 1.7566509246826172, "learning_rate": 3.1016753951589125e-05, "loss": 0.2824, "step": 4160 }, { "epoch": 1.9260969976905313, "grad_norm": 2.8334522247314453, "learning_rate": 3.0918897675749954e-05, "loss": 0.2877, "step": 4170 }, { "epoch": 1.9307159353348728, "grad_norm": 1.7744240760803223, "learning_rate": 3.0820945234434574e-05, "loss": 0.2974, "step": 4180 }, { "epoch": 1.9353348729792148, "grad_norm": 1.9070693254470825, "learning_rate": 3.072289821909526e-05, "loss": 0.2679, "step": 4190 }, { "epoch": 1.9399538106235565, "grad_norm": 1.7565782070159912, "learning_rate": 3.062475822272086e-05, "loss": 0.2855, "step": 4200 }, { "epoch": 1.9445727482678983, "grad_norm": 2.6275551319122314, "learning_rate": 3.052652683981088e-05, "loss": 0.2897, "step": 4210 }, { "epoch": 1.9491916859122402, "grad_norm": 1.8564082384109497, "learning_rate": 3.0428205666349613e-05, "loss": 0.2901, "step": 4220 }, { "epoch": 1.953810623556582, "grad_norm": 2.128941059112549, "learning_rate": 3.0329796299780194e-05, "loss": 0.2676, "step": 4230 }, { "epoch": 1.9584295612009237, "grad_norm": 1.9432369470596313, "learning_rate": 3.023130033897865e-05, "loss": 0.3301, "step": 4240 }, { "epoch": 1.9630484988452657, "grad_norm": 3.3398051261901855, "learning_rate": 3.013271938422793e-05, "loss": 0.2685, "step": 4250 }, { "epoch": 1.9676674364896074, "grad_norm": 1.5262051820755005, "learning_rate": 3.0034055037191873e-05, "loss": 0.2626, "step": 4260 }, { "epoch": 1.9722863741339491, "grad_norm": 1.130135416984558, "learning_rate": 2.9935308900889236e-05, "loss": 0.2684, "step": 4270 }, { "epoch": 1.976905311778291, "grad_norm": 2.437141180038452, "learning_rate": 2.9836482579667596e-05, "loss": 0.263, "step": 4280 }, { "epoch": 1.9815242494226328, "grad_norm": 1.438842535018921, "learning_rate": 2.973757767917734e-05, "loss": 0.3022, "step": 4290 }, { "epoch": 1.9861431870669746, "grad_norm": 2.1573774814605713, "learning_rate": 2.9638595806345514e-05, "loss": 0.2695, "step": 4300 }, { "epoch": 1.9907621247113165, "grad_norm": 1.7988911867141724, "learning_rate": 2.953953856934978e-05, "loss": 0.2483, "step": 4310 }, { "epoch": 1.995381062355658, "grad_norm": 1.6424773931503296, "learning_rate": 2.944040757759222e-05, "loss": 0.269, "step": 4320 }, { "epoch": 2.0, "grad_norm": 1.3205206394195557, "learning_rate": 2.9341204441673266e-05, "loss": 0.3165, "step": 4330 }, { "epoch": 2.004618937644342, "grad_norm": 1.0420045852661133, "learning_rate": 2.9241930773365456e-05, "loss": 0.1673, "step": 4340 }, { "epoch": 2.0092378752886835, "grad_norm": 1.3918241262435913, "learning_rate": 2.9142588185587295e-05, "loss": 0.1835, "step": 4350 }, { "epoch": 2.0138568129330254, "grad_norm": 1.5419436693191528, "learning_rate": 2.9043178292377044e-05, "loss": 0.1731, "step": 4360 }, { "epoch": 2.0184757505773674, "grad_norm": 0.961023211479187, "learning_rate": 2.8943702708866475e-05, "loss": 0.1887, "step": 4370 }, { "epoch": 2.023094688221709, "grad_norm": 0.8692442178726196, "learning_rate": 2.884416305125465e-05, "loss": 0.1627, "step": 4380 }, { "epoch": 2.027713625866051, "grad_norm": 1.6128696203231812, "learning_rate": 2.874456093678165e-05, "loss": 0.1778, "step": 4390 }, { "epoch": 2.032332563510393, "grad_norm": 1.8200603723526, "learning_rate": 2.8644897983702312e-05, "loss": 0.1916, "step": 4400 }, { "epoch": 2.0369515011547343, "grad_norm": 2.3124101161956787, "learning_rate": 2.8545175811259917e-05, "loss": 0.167, "step": 4410 }, { "epoch": 2.0415704387990763, "grad_norm": 1.1602951288223267, "learning_rate": 2.8445396039659915e-05, "loss": 0.1738, "step": 4420 }, { "epoch": 2.046189376443418, "grad_norm": 1.179870843887329, "learning_rate": 2.834556029004356e-05, "loss": 0.1846, "step": 4430 }, { "epoch": 2.0508083140877598, "grad_norm": 1.220243215560913, "learning_rate": 2.8245670184461605e-05, "loss": 0.1837, "step": 4440 }, { "epoch": 2.0554272517321017, "grad_norm": 2.2117416858673096, "learning_rate": 2.814572734584792e-05, "loss": 0.1815, "step": 4450 }, { "epoch": 2.0600461893764432, "grad_norm": 1.0153459310531616, "learning_rate": 2.8045733397993167e-05, "loss": 0.1735, "step": 4460 }, { "epoch": 2.064665127020785, "grad_norm": 1.3777629137039185, "learning_rate": 2.7945689965518358e-05, "loss": 0.1766, "step": 4470 }, { "epoch": 2.069284064665127, "grad_norm": 1.3837697505950928, "learning_rate": 2.784559867384851e-05, "loss": 0.185, "step": 4480 }, { "epoch": 2.0739030023094687, "grad_norm": 1.323298692703247, "learning_rate": 2.774546114918621e-05, "loss": 0.1924, "step": 4490 }, { "epoch": 2.0785219399538106, "grad_norm": 1.437888264656067, "learning_rate": 2.7645279018485203e-05, "loss": 0.1851, "step": 4500 }, { "epoch": 2.0831408775981526, "grad_norm": 1.245036005973816, "learning_rate": 2.7545053909423964e-05, "loss": 0.1945, "step": 4510 }, { "epoch": 2.087759815242494, "grad_norm": 1.3738816976547241, "learning_rate": 2.744478745037923e-05, "loss": 0.195, "step": 4520 }, { "epoch": 2.092378752886836, "grad_norm": 5.403616428375244, "learning_rate": 2.7344481270399575e-05, "loss": 0.1734, "step": 4530 }, { "epoch": 2.096997690531178, "grad_norm": 1.0494999885559082, "learning_rate": 2.724413699917892e-05, "loss": 0.1938, "step": 4540 }, { "epoch": 2.1016166281755195, "grad_norm": 1.6026567220687866, "learning_rate": 2.7143756267030073e-05, "loss": 0.1863, "step": 4550 }, { "epoch": 2.1062355658198615, "grad_norm": 1.5275366306304932, "learning_rate": 2.70433407048582e-05, "loss": 0.1801, "step": 4560 }, { "epoch": 2.1108545034642034, "grad_norm": 1.5171515941619873, "learning_rate": 2.6942891944134373e-05, "loss": 0.1951, "step": 4570 }, { "epoch": 2.115473441108545, "grad_norm": 1.289188265800476, "learning_rate": 2.6842411616869073e-05, "loss": 0.1766, "step": 4580 }, { "epoch": 2.120092378752887, "grad_norm": 1.2783315181732178, "learning_rate": 2.674190135558562e-05, "loss": 0.1762, "step": 4590 }, { "epoch": 2.1247113163972284, "grad_norm": 1.8653844594955444, "learning_rate": 2.6641362793293672e-05, "loss": 0.165, "step": 4600 }, { "epoch": 2.1293302540415704, "grad_norm": 0.8729211091995239, "learning_rate": 2.6540797563462722e-05, "loss": 0.1601, "step": 4610 }, { "epoch": 2.1339491916859123, "grad_norm": 1.6761512756347656, "learning_rate": 2.6440207299995513e-05, "loss": 0.18, "step": 4620 }, { "epoch": 2.138568129330254, "grad_norm": 1.1524239778518677, "learning_rate": 2.6339593637201533e-05, "loss": 0.1625, "step": 4630 }, { "epoch": 2.143187066974596, "grad_norm": 1.1707701683044434, "learning_rate": 2.6238958209770443e-05, "loss": 0.1774, "step": 4640 }, { "epoch": 2.147806004618938, "grad_norm": 1.6223604679107666, "learning_rate": 2.61383026527455e-05, "loss": 0.1946, "step": 4650 }, { "epoch": 2.1524249422632793, "grad_norm": 1.563755750656128, "learning_rate": 2.603762860149703e-05, "loss": 0.1643, "step": 4660 }, { "epoch": 2.1570438799076213, "grad_norm": 2.1498727798461914, "learning_rate": 2.593693769169583e-05, "loss": 0.169, "step": 4670 }, { "epoch": 2.161662817551963, "grad_norm": 1.2287075519561768, "learning_rate": 2.583623155928659e-05, "loss": 0.1902, "step": 4680 }, { "epoch": 2.1662817551963047, "grad_norm": 1.0633172988891602, "learning_rate": 2.5735511840461345e-05, "loss": 0.1776, "step": 4690 }, { "epoch": 2.1709006928406467, "grad_norm": 1.9634013175964355, "learning_rate": 2.5634780171632866e-05, "loss": 0.1957, "step": 4700 }, { "epoch": 2.1755196304849886, "grad_norm": 1.6423156261444092, "learning_rate": 2.553403818940807e-05, "loss": 0.1728, "step": 4710 }, { "epoch": 2.18013856812933, "grad_norm": 1.1792465448379517, "learning_rate": 2.5433287530561452e-05, "loss": 0.1682, "step": 4720 }, { "epoch": 2.184757505773672, "grad_norm": 1.0168983936309814, "learning_rate": 2.5332529832008444e-05, "loss": 0.1646, "step": 4730 }, { "epoch": 2.1893764434180136, "grad_norm": 1.7907347679138184, "learning_rate": 2.523176673077889e-05, "loss": 0.1929, "step": 4740 }, { "epoch": 2.1939953810623556, "grad_norm": 1.1417113542556763, "learning_rate": 2.5130999863990402e-05, "loss": 0.1734, "step": 4750 }, { "epoch": 2.1986143187066975, "grad_norm": 1.4063057899475098, "learning_rate": 2.5030230868821764e-05, "loss": 0.182, "step": 4760 }, { "epoch": 2.203233256351039, "grad_norm": 1.541481614112854, "learning_rate": 2.4929461382486356e-05, "loss": 0.175, "step": 4770 }, { "epoch": 2.207852193995381, "grad_norm": 1.8193329572677612, "learning_rate": 2.4828693042205513e-05, "loss": 0.1759, "step": 4780 }, { "epoch": 2.212471131639723, "grad_norm": 2.088608503341675, "learning_rate": 2.472792748518198e-05, "loss": 0.1702, "step": 4790 }, { "epoch": 2.2170900692840645, "grad_norm": 0.9524586200714111, "learning_rate": 2.4627166348573256e-05, "loss": 0.1677, "step": 4800 }, { "epoch": 2.2217090069284064, "grad_norm": 1.448237419128418, "learning_rate": 2.452641126946503e-05, "loss": 0.1499, "step": 4810 }, { "epoch": 2.2263279445727484, "grad_norm": 1.7067848443984985, "learning_rate": 2.4425663884844577e-05, "loss": 0.1731, "step": 4820 }, { "epoch": 2.23094688221709, "grad_norm": 1.2335261106491089, "learning_rate": 2.4324925831574162e-05, "loss": 0.182, "step": 4830 }, { "epoch": 2.235565819861432, "grad_norm": 1.4744840860366821, "learning_rate": 2.4224198746364422e-05, "loss": 0.1831, "step": 4840 }, { "epoch": 2.240184757505774, "grad_norm": 1.967423915863037, "learning_rate": 2.412348426574782e-05, "loss": 0.1704, "step": 4850 }, { "epoch": 2.2448036951501154, "grad_norm": 1.8442059755325317, "learning_rate": 2.4022784026052002e-05, "loss": 0.174, "step": 4860 }, { "epoch": 2.2494226327944573, "grad_norm": 0.9935666918754578, "learning_rate": 2.392209966337327e-05, "loss": 0.1499, "step": 4870 }, { "epoch": 2.2540415704387993, "grad_norm": 1.3703944683074951, "learning_rate": 2.382143281354995e-05, "loss": 0.1975, "step": 4880 }, { "epoch": 2.258660508083141, "grad_norm": 1.297925591468811, "learning_rate": 2.3720785112135826e-05, "loss": 0.1694, "step": 4890 }, { "epoch": 2.2632794457274827, "grad_norm": 1.4075946807861328, "learning_rate": 2.36201581943736e-05, "loss": 0.1795, "step": 4900 }, { "epoch": 2.2678983833718247, "grad_norm": 2.089986801147461, "learning_rate": 2.351955369516826e-05, "loss": 0.194, "step": 4910 }, { "epoch": 2.272517321016166, "grad_norm": 2.0710537433624268, "learning_rate": 2.341897324906061e-05, "loss": 0.1862, "step": 4920 }, { "epoch": 2.277136258660508, "grad_norm": 2.116464853286743, "learning_rate": 2.3318418490200595e-05, "loss": 0.1924, "step": 4930 }, { "epoch": 2.28175519630485, "grad_norm": 1.4657981395721436, "learning_rate": 2.3217891052320855e-05, "loss": 0.168, "step": 4940 }, { "epoch": 2.2863741339491916, "grad_norm": 1.6012533903121948, "learning_rate": 2.3117392568710143e-05, "loss": 0.1816, "step": 4950 }, { "epoch": 2.2909930715935336, "grad_norm": 1.3093957901000977, "learning_rate": 2.301692467218677e-05, "loss": 0.1765, "step": 4960 }, { "epoch": 2.295612009237875, "grad_norm": 1.3413617610931396, "learning_rate": 2.291648899507208e-05, "loss": 0.1968, "step": 4970 }, { "epoch": 2.300230946882217, "grad_norm": 1.4735230207443237, "learning_rate": 2.2816087169163987e-05, "loss": 0.1802, "step": 4980 }, { "epoch": 2.304849884526559, "grad_norm": 1.670451283454895, "learning_rate": 2.271572082571036e-05, "loss": 0.1645, "step": 4990 }, { "epoch": 2.3094688221709005, "grad_norm": 1.1457953453063965, "learning_rate": 2.261539159538264e-05, "loss": 0.1905, "step": 5000 }, { "epoch": 2.3140877598152425, "grad_norm": 2.7969279289245605, "learning_rate": 2.2515101108249235e-05, "loss": 0.174, "step": 5010 }, { "epoch": 2.3187066974595845, "grad_norm": 1.7321696281433105, "learning_rate": 2.2414850993749097e-05, "loss": 0.1715, "step": 5020 }, { "epoch": 2.323325635103926, "grad_norm": 1.2443653345108032, "learning_rate": 2.2314642880665257e-05, "loss": 0.1673, "step": 5030 }, { "epoch": 2.327944572748268, "grad_norm": 1.1120126247406006, "learning_rate": 2.2214478397098304e-05, "loss": 0.1683, "step": 5040 }, { "epoch": 2.3325635103926095, "grad_norm": 2.85561466217041, "learning_rate": 2.2114359170440004e-05, "loss": 0.1887, "step": 5050 }, { "epoch": 2.3371824480369514, "grad_norm": 2.454183578491211, "learning_rate": 2.201428682734682e-05, "loss": 0.1808, "step": 5060 }, { "epoch": 2.3418013856812934, "grad_norm": 1.4741981029510498, "learning_rate": 2.1914262993713454e-05, "loss": 0.1889, "step": 5070 }, { "epoch": 2.346420323325635, "grad_norm": 1.6135503053665161, "learning_rate": 2.181428929464652e-05, "loss": 0.1664, "step": 5080 }, { "epoch": 2.351039260969977, "grad_norm": 1.3496638536453247, "learning_rate": 2.1714367354438046e-05, "loss": 0.1722, "step": 5090 }, { "epoch": 2.355658198614319, "grad_norm": 2.5449349880218506, "learning_rate": 2.1614498796539124e-05, "loss": 0.1825, "step": 5100 }, { "epoch": 2.3602771362586603, "grad_norm": 1.0597965717315674, "learning_rate": 2.151468524353356e-05, "loss": 0.1738, "step": 5110 }, { "epoch": 2.3648960739030023, "grad_norm": 1.8311617374420166, "learning_rate": 2.141492831711146e-05, "loss": 0.1902, "step": 5120 }, { "epoch": 2.3695150115473442, "grad_norm": 1.4360136985778809, "learning_rate": 2.1315229638042934e-05, "loss": 0.1746, "step": 5130 }, { "epoch": 2.3741339491916857, "grad_norm": 1.78957998752594, "learning_rate": 2.1215590826151705e-05, "loss": 0.1542, "step": 5140 }, { "epoch": 2.3787528868360277, "grad_norm": 1.497788429260254, "learning_rate": 2.1116013500288824e-05, "loss": 0.165, "step": 5150 }, { "epoch": 2.3833718244803697, "grad_norm": 1.6228641271591187, "learning_rate": 2.1016499278306405e-05, "loss": 0.2035, "step": 5160 }, { "epoch": 2.387990762124711, "grad_norm": 1.008284568786621, "learning_rate": 2.091704977703125e-05, "loss": 0.1668, "step": 5170 }, { "epoch": 2.392609699769053, "grad_norm": 1.4382859468460083, "learning_rate": 2.0817666612238673e-05, "loss": 0.1701, "step": 5180 }, { "epoch": 2.397228637413395, "grad_norm": 2.184495449066162, "learning_rate": 2.071835139862619e-05, "loss": 0.1747, "step": 5190 }, { "epoch": 2.4018475750577366, "grad_norm": 1.1393109560012817, "learning_rate": 2.061910574978728e-05, "loss": 0.1711, "step": 5200 }, { "epoch": 2.4064665127020786, "grad_norm": 0.905232310295105, "learning_rate": 2.051993127818524e-05, "loss": 0.1883, "step": 5210 }, { "epoch": 2.4110854503464205, "grad_norm": 1.4757813215255737, "learning_rate": 2.0420829595126872e-05, "loss": 0.1912, "step": 5220 }, { "epoch": 2.415704387990762, "grad_norm": 1.5557478666305542, "learning_rate": 2.0321802310736433e-05, "loss": 0.194, "step": 5230 }, { "epoch": 2.420323325635104, "grad_norm": 1.237066388130188, "learning_rate": 2.0222851033929367e-05, "loss": 0.1777, "step": 5240 }, { "epoch": 2.424942263279446, "grad_norm": 1.6757056713104248, "learning_rate": 2.012397737238621e-05, "loss": 0.1687, "step": 5250 }, { "epoch": 2.4295612009237875, "grad_norm": 1.3317631483078003, "learning_rate": 2.0025182932526507e-05, "loss": 0.1751, "step": 5260 }, { "epoch": 2.4341801385681294, "grad_norm": 1.1756433248519897, "learning_rate": 1.9926469319482628e-05, "loss": 0.159, "step": 5270 }, { "epoch": 2.438799076212471, "grad_norm": 1.385180115699768, "learning_rate": 1.9827838137073743e-05, "loss": 0.1603, "step": 5280 }, { "epoch": 2.443418013856813, "grad_norm": 1.442808747291565, "learning_rate": 1.9729290987779777e-05, "loss": 0.1729, "step": 5290 }, { "epoch": 2.448036951501155, "grad_norm": 1.2186540365219116, "learning_rate": 1.9630829472715337e-05, "loss": 0.1744, "step": 5300 }, { "epoch": 2.4526558891454964, "grad_norm": 1.4557946920394897, "learning_rate": 1.9532455191603715e-05, "loss": 0.1713, "step": 5310 }, { "epoch": 2.4572748267898383, "grad_norm": 1.2399466037750244, "learning_rate": 1.9434169742750906e-05, "loss": 0.175, "step": 5320 }, { "epoch": 2.4618937644341803, "grad_norm": 1.5492390394210815, "learning_rate": 1.93359747230196e-05, "loss": 0.1809, "step": 5330 }, { "epoch": 2.466512702078522, "grad_norm": 1.8851852416992188, "learning_rate": 1.9237871727803314e-05, "loss": 0.1842, "step": 5340 }, { "epoch": 2.4711316397228638, "grad_norm": 1.4627329111099243, "learning_rate": 1.9139862351000383e-05, "loss": 0.1682, "step": 5350 }, { "epoch": 2.4757505773672057, "grad_norm": 1.6467459201812744, "learning_rate": 1.904194818498813e-05, "loss": 0.1761, "step": 5360 }, { "epoch": 2.4803695150115472, "grad_norm": 1.3768023252487183, "learning_rate": 1.8944130820596967e-05, "loss": 0.1675, "step": 5370 }, { "epoch": 2.484988452655889, "grad_norm": 2.7051913738250732, "learning_rate": 1.884641184708453e-05, "loss": 0.1686, "step": 5380 }, { "epoch": 2.4896073903002307, "grad_norm": 1.4548815488815308, "learning_rate": 1.874879285210992e-05, "loss": 0.1695, "step": 5390 }, { "epoch": 2.4942263279445727, "grad_norm": 1.246937870979309, "learning_rate": 1.8651275421707835e-05, "loss": 0.1601, "step": 5400 }, { "epoch": 2.4988452655889146, "grad_norm": 1.1435866355895996, "learning_rate": 1.8553861140262824e-05, "loss": 0.1701, "step": 5410 }, { "epoch": 2.503464203233256, "grad_norm": 1.1018195152282715, "learning_rate": 1.8456551590483596e-05, "loss": 0.1798, "step": 5420 }, { "epoch": 2.508083140877598, "grad_norm": 1.4041470289230347, "learning_rate": 1.8359348353377226e-05, "loss": 0.1747, "step": 5430 }, { "epoch": 2.51270207852194, "grad_norm": 1.0429677963256836, "learning_rate": 1.826225300822354e-05, "loss": 0.1777, "step": 5440 }, { "epoch": 2.5173210161662816, "grad_norm": 1.4189164638519287, "learning_rate": 1.8165267132549398e-05, "loss": 0.1701, "step": 5450 }, { "epoch": 2.5219399538106235, "grad_norm": 1.2409905195236206, "learning_rate": 1.8068392302103075e-05, "loss": 0.1715, "step": 5460 }, { "epoch": 2.5265588914549655, "grad_norm": 1.2827545404434204, "learning_rate": 1.7971630090828713e-05, "loss": 0.1883, "step": 5470 }, { "epoch": 2.531177829099307, "grad_norm": 1.7266392707824707, "learning_rate": 1.7874982070840684e-05, "loss": 0.178, "step": 5480 }, { "epoch": 2.535796766743649, "grad_norm": 1.0178502798080444, "learning_rate": 1.7778449812398078e-05, "loss": 0.1535, "step": 5490 }, { "epoch": 2.540415704387991, "grad_norm": 2.1752450466156006, "learning_rate": 1.7682034883879183e-05, "loss": 0.176, "step": 5500 }, { "epoch": 2.5450346420323324, "grad_norm": 5.4677510261535645, "learning_rate": 1.7585738851755993e-05, "loss": 0.1764, "step": 5510 }, { "epoch": 2.5496535796766744, "grad_norm": 1.5139080286026, "learning_rate": 1.7489563280568803e-05, "loss": 0.1663, "step": 5520 }, { "epoch": 2.5542725173210163, "grad_norm": 1.7427213191986084, "learning_rate": 1.7393509732900713e-05, "loss": 0.1641, "step": 5530 }, { "epoch": 2.558891454965358, "grad_norm": 1.0485565662384033, "learning_rate": 1.7297579769352306e-05, "loss": 0.172, "step": 5540 }, { "epoch": 2.5635103926097, "grad_norm": 1.7928640842437744, "learning_rate": 1.7201774948516287e-05, "loss": 0.1528, "step": 5550 }, { "epoch": 2.5681293302540418, "grad_norm": 1.1887588500976562, "learning_rate": 1.7106096826952094e-05, "loss": 0.1839, "step": 5560 }, { "epoch": 2.5727482678983833, "grad_norm": 1.5354337692260742, "learning_rate": 1.701054695916072e-05, "loss": 0.1697, "step": 5570 }, { "epoch": 2.5773672055427252, "grad_norm": 1.7991998195648193, "learning_rate": 1.6915126897559348e-05, "loss": 0.1815, "step": 5580 }, { "epoch": 2.581986143187067, "grad_norm": 1.2599282264709473, "learning_rate": 1.6819838192456177e-05, "loss": 0.1739, "step": 5590 }, { "epoch": 2.5866050808314087, "grad_norm": 1.4219754934310913, "learning_rate": 1.6724682392025256e-05, "loss": 0.1687, "step": 5600 }, { "epoch": 2.5912240184757507, "grad_norm": 2.3034982681274414, "learning_rate": 1.6629661042281287e-05, "loss": 0.1815, "step": 5610 }, { "epoch": 2.5958429561200926, "grad_norm": 1.3166123628616333, "learning_rate": 1.6534775687054544e-05, "loss": 0.1681, "step": 5620 }, { "epoch": 2.600461893764434, "grad_norm": 1.8826807737350464, "learning_rate": 1.644002786796575e-05, "loss": 0.1889, "step": 5630 }, { "epoch": 2.605080831408776, "grad_norm": 1.6106212139129639, "learning_rate": 1.6345419124401052e-05, "loss": 0.1615, "step": 5640 }, { "epoch": 2.6096997690531176, "grad_norm": 1.898163914680481, "learning_rate": 1.6250950993487035e-05, "loss": 0.1781, "step": 5650 }, { "epoch": 2.6143187066974596, "grad_norm": 0.9831230044364929, "learning_rate": 1.61566250100657e-05, "loss": 0.1604, "step": 5660 }, { "epoch": 2.6189376443418015, "grad_norm": 1.5280791521072388, "learning_rate": 1.606244270666955e-05, "loss": 0.1517, "step": 5670 }, { "epoch": 2.623556581986143, "grad_norm": 1.33904230594635, "learning_rate": 1.5968405613496722e-05, "loss": 0.189, "step": 5680 }, { "epoch": 2.628175519630485, "grad_norm": 1.6268576383590698, "learning_rate": 1.587451525838604e-05, "loss": 0.1601, "step": 5690 }, { "epoch": 2.6327944572748265, "grad_norm": 1.558390498161316, "learning_rate": 1.5780773166792306e-05, "loss": 0.1784, "step": 5700 }, { "epoch": 2.6374133949191685, "grad_norm": 1.1585159301757812, "learning_rate": 1.5687180861761407e-05, "loss": 0.1636, "step": 5710 }, { "epoch": 2.6420323325635104, "grad_norm": 1.5481468439102173, "learning_rate": 1.559373986390565e-05, "loss": 0.178, "step": 5720 }, { "epoch": 2.646651270207852, "grad_norm": 2.045743703842163, "learning_rate": 1.5500451691379003e-05, "loss": 0.1838, "step": 5730 }, { "epoch": 2.651270207852194, "grad_norm": 2.1467044353485107, "learning_rate": 1.5407317859852466e-05, "loss": 0.2045, "step": 5740 }, { "epoch": 2.655889145496536, "grad_norm": 0.9179111123085022, "learning_rate": 1.5314339882489438e-05, "loss": 0.1996, "step": 5750 }, { "epoch": 2.6605080831408774, "grad_norm": 1.4354523420333862, "learning_rate": 1.5221519269921103e-05, "loss": 0.1815, "step": 5760 }, { "epoch": 2.6651270207852193, "grad_norm": 1.3646310567855835, "learning_rate": 1.5128857530221909e-05, "loss": 0.1591, "step": 5770 }, { "epoch": 2.6697459584295613, "grad_norm": 1.5501469373703003, "learning_rate": 1.5036356168885099e-05, "loss": 0.1857, "step": 5780 }, { "epoch": 2.674364896073903, "grad_norm": 1.8186252117156982, "learning_rate": 1.494401668879819e-05, "loss": 0.1658, "step": 5790 }, { "epoch": 2.678983833718245, "grad_norm": 1.589977502822876, "learning_rate": 1.4851840590218572e-05, "loss": 0.1821, "step": 5800 }, { "epoch": 2.6836027713625867, "grad_norm": 1.0447371006011963, "learning_rate": 1.4759829370749184e-05, "loss": 0.1547, "step": 5810 }, { "epoch": 2.6882217090069283, "grad_norm": 1.9841195344924927, "learning_rate": 1.4667984525314093e-05, "loss": 0.1863, "step": 5820 }, { "epoch": 2.69284064665127, "grad_norm": 1.720861792564392, "learning_rate": 1.4576307546134302e-05, "loss": 0.1863, "step": 5830 }, { "epoch": 2.697459584295612, "grad_norm": 0.9082615971565247, "learning_rate": 1.4484799922703435e-05, "loss": 0.1716, "step": 5840 }, { "epoch": 2.7020785219399537, "grad_norm": 1.7083011865615845, "learning_rate": 1.4393463141763541e-05, "loss": 0.1732, "step": 5850 }, { "epoch": 2.7066974595842956, "grad_norm": 2.1367697715759277, "learning_rate": 1.4302298687281007e-05, "loss": 0.1914, "step": 5860 }, { "epoch": 2.7113163972286376, "grad_norm": 0.8921797871589661, "learning_rate": 1.421130804042235e-05, "loss": 0.1775, "step": 5870 }, { "epoch": 2.715935334872979, "grad_norm": 1.0890942811965942, "learning_rate": 1.4120492679530237e-05, "loss": 0.1465, "step": 5880 }, { "epoch": 2.720554272517321, "grad_norm": 1.6897724866867065, "learning_rate": 1.4029854080099408e-05, "loss": 0.1697, "step": 5890 }, { "epoch": 2.725173210161663, "grad_norm": 1.3306939601898193, "learning_rate": 1.3939393714752722e-05, "loss": 0.1584, "step": 5900 }, { "epoch": 2.7297921478060045, "grad_norm": 1.2497321367263794, "learning_rate": 1.384911305321726e-05, "loss": 0.1614, "step": 5910 }, { "epoch": 2.7344110854503465, "grad_norm": 1.698232650756836, "learning_rate": 1.3759013562300393e-05, "loss": 0.1677, "step": 5920 }, { "epoch": 2.7390300230946885, "grad_norm": 3.738900899887085, "learning_rate": 1.3669096705866008e-05, "loss": 0.169, "step": 5930 }, { "epoch": 2.74364896073903, "grad_norm": 1.3388948440551758, "learning_rate": 1.3579363944810647e-05, "loss": 0.1636, "step": 5940 }, { "epoch": 2.748267898383372, "grad_norm": 1.0442326068878174, "learning_rate": 1.3489816737039867e-05, "loss": 0.1597, "step": 5950 }, { "epoch": 2.752886836027714, "grad_norm": 1.409279227256775, "learning_rate": 1.3400456537444492e-05, "loss": 0.1715, "step": 5960 }, { "epoch": 2.7575057736720554, "grad_norm": 1.5920976400375366, "learning_rate": 1.3311284797876971e-05, "loss": 0.1674, "step": 5970 }, { "epoch": 2.7621247113163974, "grad_norm": 2.0098776817321777, "learning_rate": 1.3222302967127809e-05, "loss": 0.1933, "step": 5980 }, { "epoch": 2.766743648960739, "grad_norm": 0.9214677810668945, "learning_rate": 1.313351249090205e-05, "loss": 0.1483, "step": 5990 }, { "epoch": 2.771362586605081, "grad_norm": 1.4411190748214722, "learning_rate": 1.3044914811795734e-05, "loss": 0.1674, "step": 6000 }, { "epoch": 2.775981524249423, "grad_norm": 1.1255160570144653, "learning_rate": 1.2956511369272515e-05, "loss": 0.1483, "step": 6010 }, { "epoch": 2.7806004618937643, "grad_norm": 1.1127042770385742, "learning_rate": 1.2868303599640227e-05, "loss": 0.1847, "step": 6020 }, { "epoch": 2.7852193995381063, "grad_norm": 1.2573184967041016, "learning_rate": 1.2780292936027572e-05, "loss": 0.1801, "step": 6030 }, { "epoch": 2.789838337182448, "grad_norm": 1.572396993637085, "learning_rate": 1.2692480808360851e-05, "loss": 0.1617, "step": 6040 }, { "epoch": 2.7944572748267897, "grad_norm": 1.4040261507034302, "learning_rate": 1.2604868643340684e-05, "loss": 0.165, "step": 6050 }, { "epoch": 2.7990762124711317, "grad_norm": 2.0728392601013184, "learning_rate": 1.251745786441888e-05, "loss": 0.1602, "step": 6060 }, { "epoch": 2.803695150115473, "grad_norm": 1.33614182472229, "learning_rate": 1.2430249891775295e-05, "loss": 0.172, "step": 6070 }, { "epoch": 2.808314087759815, "grad_norm": 1.7234444618225098, "learning_rate": 1.2343246142294723e-05, "loss": 0.18, "step": 6080 }, { "epoch": 2.812933025404157, "grad_norm": 1.4928007125854492, "learning_rate": 1.225644802954394e-05, "loss": 0.1696, "step": 6090 }, { "epoch": 2.8175519630484986, "grad_norm": 1.20448637008667, "learning_rate": 1.2169856963748675e-05, "loss": 0.1582, "step": 6100 }, { "epoch": 2.8221709006928406, "grad_norm": 4.563014030456543, "learning_rate": 1.2083474351770724e-05, "loss": 0.1747, "step": 6110 }, { "epoch": 2.8267898383371826, "grad_norm": 2.7640464305877686, "learning_rate": 1.1997301597085123e-05, "loss": 0.1675, "step": 6120 }, { "epoch": 2.831408775981524, "grad_norm": 2.275937795639038, "learning_rate": 1.1911340099757281e-05, "loss": 0.167, "step": 6130 }, { "epoch": 2.836027713625866, "grad_norm": 1.6117650270462036, "learning_rate": 1.1825591256420302e-05, "loss": 0.1598, "step": 6140 }, { "epoch": 2.840646651270208, "grad_norm": 1.077294945716858, "learning_rate": 1.174005646025223e-05, "loss": 0.1741, "step": 6150 }, { "epoch": 2.8452655889145495, "grad_norm": 1.3975902795791626, "learning_rate": 1.1654737100953447e-05, "loss": 0.1637, "step": 6160 }, { "epoch": 2.8498845265588915, "grad_norm": 1.73171067237854, "learning_rate": 1.1569634564724105e-05, "loss": 0.1607, "step": 6170 }, { "epoch": 2.8545034642032334, "grad_norm": 1.1392546892166138, "learning_rate": 1.1484750234241595e-05, "loss": 0.1615, "step": 6180 }, { "epoch": 2.859122401847575, "grad_norm": 1.2370185852050781, "learning_rate": 1.1400085488638044e-05, "loss": 0.1499, "step": 6190 }, { "epoch": 2.863741339491917, "grad_norm": 1.2709741592407227, "learning_rate": 1.131564170347798e-05, "loss": 0.1713, "step": 6200 }, { "epoch": 2.868360277136259, "grad_norm": 1.0835464000701904, "learning_rate": 1.1231420250735908e-05, "loss": 0.1454, "step": 6210 }, { "epoch": 2.8729792147806004, "grad_norm": 1.5020650625228882, "learning_rate": 1.114742249877409e-05, "loss": 0.161, "step": 6220 }, { "epoch": 2.8775981524249423, "grad_norm": 1.4749438762664795, "learning_rate": 1.1063649812320254e-05, "loss": 0.1474, "step": 6230 }, { "epoch": 2.8822170900692843, "grad_norm": 3.8500893115997314, "learning_rate": 1.0980103552445442e-05, "loss": 0.1706, "step": 6240 }, { "epoch": 2.886836027713626, "grad_norm": 1.0030537843704224, "learning_rate": 1.0896785076541923e-05, "loss": 0.1699, "step": 6250 }, { "epoch": 2.8914549653579678, "grad_norm": 1.5781772136688232, "learning_rate": 1.0813695738301094e-05, "loss": 0.1791, "step": 6260 }, { "epoch": 2.8960739030023097, "grad_norm": 1.3969545364379883, "learning_rate": 1.0730836887691522e-05, "loss": 0.185, "step": 6270 }, { "epoch": 2.9006928406466512, "grad_norm": 1.7544200420379639, "learning_rate": 1.0648209870936993e-05, "loss": 0.1712, "step": 6280 }, { "epoch": 2.905311778290993, "grad_norm": 2.34084415435791, "learning_rate": 1.0565816030494626e-05, "loss": 0.1835, "step": 6290 }, { "epoch": 2.909930715935335, "grad_norm": 1.3671057224273682, "learning_rate": 1.0483656705033107e-05, "loss": 0.1642, "step": 6300 }, { "epoch": 2.9145496535796767, "grad_norm": 1.4023957252502441, "learning_rate": 1.0401733229410906e-05, "loss": 0.1512, "step": 6310 }, { "epoch": 2.9191685912240186, "grad_norm": 3.9713752269744873, "learning_rate": 1.0320046934654576e-05, "loss": 0.1704, "step": 6320 }, { "epoch": 2.92378752886836, "grad_norm": 1.8375264406204224, "learning_rate": 1.023859914793717e-05, "loss": 0.1709, "step": 6330 }, { "epoch": 2.928406466512702, "grad_norm": 1.215713381767273, "learning_rate": 1.0157391192556629e-05, "loss": 0.1717, "step": 6340 }, { "epoch": 2.9330254041570436, "grad_norm": 1.7471559047698975, "learning_rate": 1.007642438791434e-05, "loss": 0.2006, "step": 6350 }, { "epoch": 2.9376443418013856, "grad_norm": 1.2986832857131958, "learning_rate": 9.995700049493644e-06, "loss": 0.1489, "step": 6360 }, { "epoch": 2.9422632794457275, "grad_norm": 1.6584694385528564, "learning_rate": 9.915219488838482e-06, "loss": 0.1696, "step": 6370 }, { "epoch": 2.946882217090069, "grad_norm": 2.0090951919555664, "learning_rate": 9.834984013532116e-06, "loss": 0.1531, "step": 6380 }, { "epoch": 2.951501154734411, "grad_norm": 1.7718456983566284, "learning_rate": 9.754994927175828e-06, "loss": 0.1514, "step": 6390 }, { "epoch": 2.956120092378753, "grad_norm": 1.5160819292068481, "learning_rate": 9.67525352936781e-06, "loss": 0.1765, "step": 6400 }, { "epoch": 2.9607390300230945, "grad_norm": 1.3446481227874756, "learning_rate": 9.595761115681957e-06, "loss": 0.1773, "step": 6410 }, { "epoch": 2.9653579676674364, "grad_norm": 1.5220271348953247, "learning_rate": 9.516518977646929e-06, "loss": 0.1697, "step": 6420 }, { "epoch": 2.9699769053117784, "grad_norm": 1.0612167119979858, "learning_rate": 9.43752840272506e-06, "loss": 0.1603, "step": 6430 }, { "epoch": 2.97459584295612, "grad_norm": 1.0048389434814453, "learning_rate": 9.358790674291527e-06, "loss": 0.1547, "step": 6440 }, { "epoch": 2.979214780600462, "grad_norm": 2.4720213413238525, "learning_rate": 9.280307071613426e-06, "loss": 0.1822, "step": 6450 }, { "epoch": 2.983833718244804, "grad_norm": 1.2795124053955078, "learning_rate": 9.20207886982906e-06, "loss": 0.1635, "step": 6460 }, { "epoch": 2.9884526558891453, "grad_norm": 2.0103607177734375, "learning_rate": 9.124107339927148e-06, "loss": 0.1881, "step": 6470 }, { "epoch": 2.9930715935334873, "grad_norm": 1.4228339195251465, "learning_rate": 9.046393748726245e-06, "loss": 0.1551, "step": 6480 }, { "epoch": 2.9976905311778292, "grad_norm": 1.4502146244049072, "learning_rate": 8.968939358854104e-06, "loss": 0.1787, "step": 6490 }, { "epoch": 3.0023094688221708, "grad_norm": 0.9911340475082397, "learning_rate": 8.891745428727178e-06, "loss": 0.1394, "step": 6500 }, { "epoch": 3.0069284064665127, "grad_norm": 0.8997665643692017, "learning_rate": 8.814813212530207e-06, "loss": 0.1309, "step": 6510 }, { "epoch": 3.0115473441108547, "grad_norm": 0.9880512356758118, "learning_rate": 8.738143960195786e-06, "loss": 0.125, "step": 6520 }, { "epoch": 3.016166281755196, "grad_norm": 1.02323579788208, "learning_rate": 8.66173891738411e-06, "loss": 0.1168, "step": 6530 }, { "epoch": 3.020785219399538, "grad_norm": 1.122694730758667, "learning_rate": 8.585599325462685e-06, "loss": 0.1073, "step": 6540 }, { "epoch": 3.02540415704388, "grad_norm": 0.7706530094146729, "learning_rate": 8.509726421486205e-06, "loss": 0.1334, "step": 6550 }, { "epoch": 3.0300230946882216, "grad_norm": 1.3971295356750488, "learning_rate": 8.43412143817644e-06, "loss": 0.1359, "step": 6560 }, { "epoch": 3.0346420323325636, "grad_norm": 1.1861189603805542, "learning_rate": 8.358785603902175e-06, "loss": 0.1218, "step": 6570 }, { "epoch": 3.0392609699769055, "grad_norm": 1.2742732763290405, "learning_rate": 8.283720142659283e-06, "loss": 0.1311, "step": 6580 }, { "epoch": 3.043879907621247, "grad_norm": 0.8163214921951294, "learning_rate": 8.20892627405086e-06, "loss": 0.1206, "step": 6590 }, { "epoch": 3.048498845265589, "grad_norm": 1.0596466064453125, "learning_rate": 8.134405213267351e-06, "loss": 0.1099, "step": 6600 }, { "epoch": 3.0531177829099305, "grad_norm": 0.9555152058601379, "learning_rate": 8.06015817106687e-06, "loss": 0.1107, "step": 6610 }, { "epoch": 3.0577367205542725, "grad_norm": 1.061698317527771, "learning_rate": 7.986186353755479e-06, "loss": 0.1151, "step": 6620 }, { "epoch": 3.0623556581986144, "grad_norm": 1.7270359992980957, "learning_rate": 7.912490963167595e-06, "loss": 0.1084, "step": 6630 }, { "epoch": 3.066974595842956, "grad_norm": 1.2087693214416504, "learning_rate": 7.83907319664652e-06, "loss": 0.1234, "step": 6640 }, { "epoch": 3.071593533487298, "grad_norm": 0.921705961227417, "learning_rate": 7.765934247024895e-06, "loss": 0.1133, "step": 6650 }, { "epoch": 3.07621247113164, "grad_norm": 1.603304147720337, "learning_rate": 7.6930753026054e-06, "loss": 0.1122, "step": 6660 }, { "epoch": 3.0808314087759814, "grad_norm": 1.1088101863861084, "learning_rate": 7.6204975471414145e-06, "loss": 0.1196, "step": 6670 }, { "epoch": 3.0854503464203233, "grad_norm": 4.059700965881348, "learning_rate": 7.548202159817766e-06, "loss": 0.1095, "step": 6680 }, { "epoch": 3.0900692840646653, "grad_norm": 1.190368413925171, "learning_rate": 7.476190315231624e-06, "loss": 0.1122, "step": 6690 }, { "epoch": 3.094688221709007, "grad_norm": 0.6123886704444885, "learning_rate": 7.4044631833733475e-06, "loss": 0.1179, "step": 6700 }, { "epoch": 3.0993071593533488, "grad_norm": 0.9663934707641602, "learning_rate": 7.333021929607545e-06, "loss": 0.1254, "step": 6710 }, { "epoch": 3.1039260969976907, "grad_norm": 0.7853173017501831, "learning_rate": 7.261867714654092e-06, "loss": 0.1329, "step": 6720 }, { "epoch": 3.1085450346420322, "grad_norm": 0.8501221537590027, "learning_rate": 7.191001694569277e-06, "loss": 0.1096, "step": 6730 }, { "epoch": 3.113163972286374, "grad_norm": 0.9862359166145325, "learning_rate": 7.120425020727067e-06, "loss": 0.1194, "step": 6740 }, { "epoch": 3.1177829099307157, "grad_norm": 1.053269863128662, "learning_rate": 7.050138839800332e-06, "loss": 0.1181, "step": 6750 }, { "epoch": 3.1224018475750577, "grad_norm": 1.3188560009002686, "learning_rate": 6.980144293742252e-06, "loss": 0.1092, "step": 6760 }, { "epoch": 3.1270207852193996, "grad_norm": 1.166616678237915, "learning_rate": 6.910442519767782e-06, "loss": 0.1139, "step": 6770 }, { "epoch": 3.131639722863741, "grad_norm": 0.850664496421814, "learning_rate": 6.841034650335115e-06, "loss": 0.1232, "step": 6780 }, { "epoch": 3.136258660508083, "grad_norm": 0.9201288819313049, "learning_rate": 6.7719218131273494e-06, "loss": 0.1212, "step": 6790 }, { "epoch": 3.140877598152425, "grad_norm": 0.7694472670555115, "learning_rate": 6.70310513103414e-06, "loss": 0.1321, "step": 6800 }, { "epoch": 3.1454965357967666, "grad_norm": 1.0745315551757812, "learning_rate": 6.634585722133421e-06, "loss": 0.1097, "step": 6810 }, { "epoch": 3.1501154734411085, "grad_norm": 1.065644383430481, "learning_rate": 6.566364699673311e-06, "loss": 0.1308, "step": 6820 }, { "epoch": 3.1547344110854505, "grad_norm": 1.8619019985198975, "learning_rate": 6.49844317205395e-06, "loss": 0.1113, "step": 6830 }, { "epoch": 3.159353348729792, "grad_norm": 1.0731322765350342, "learning_rate": 6.430822242809559e-06, "loss": 0.1219, "step": 6840 }, { "epoch": 3.163972286374134, "grad_norm": 1.168002963066101, "learning_rate": 6.363503010590455e-06, "loss": 0.114, "step": 6850 }, { "epoch": 3.168591224018476, "grad_norm": 0.9014056324958801, "learning_rate": 6.296486569145229e-06, "loss": 0.1018, "step": 6860 }, { "epoch": 3.1732101616628174, "grad_norm": 1.1029860973358154, "learning_rate": 6.229774007302991e-06, "loss": 0.1324, "step": 6870 }, { "epoch": 3.1778290993071594, "grad_norm": 0.8068972826004028, "learning_rate": 6.16336640895564e-06, "loss": 0.0978, "step": 6880 }, { "epoch": 3.1824480369515014, "grad_norm": 0.7868428826332092, "learning_rate": 6.097264853040272e-06, "loss": 0.1185, "step": 6890 }, { "epoch": 3.187066974595843, "grad_norm": 1.155489444732666, "learning_rate": 6.03147041352167e-06, "loss": 0.1048, "step": 6900 }, { "epoch": 3.191685912240185, "grad_norm": 1.6012282371520996, "learning_rate": 5.96598415937483e-06, "loss": 0.1302, "step": 6910 }, { "epoch": 3.196304849884527, "grad_norm": 1.3077887296676636, "learning_rate": 5.900807154567589e-06, "loss": 0.1171, "step": 6920 }, { "epoch": 3.2009237875288683, "grad_norm": 0.9981237053871155, "learning_rate": 5.8359404580433735e-06, "loss": 0.1136, "step": 6930 }, { "epoch": 3.2055427251732103, "grad_norm": 1.2850341796875, "learning_rate": 5.77138512370394e-06, "loss": 0.1107, "step": 6940 }, { "epoch": 3.2101616628175518, "grad_norm": 0.8243064880371094, "learning_rate": 5.707142200392321e-06, "loss": 0.0991, "step": 6950 }, { "epoch": 3.2147806004618937, "grad_norm": 0.8430233597755432, "learning_rate": 5.643212731875705e-06, "loss": 0.1272, "step": 6960 }, { "epoch": 3.2193995381062357, "grad_norm": 1.1867564916610718, "learning_rate": 5.579597756828564e-06, "loss": 0.1155, "step": 6970 }, { "epoch": 3.224018475750577, "grad_norm": 2.0662741661071777, "learning_rate": 5.5162983088156955e-06, "loss": 0.1097, "step": 6980 }, { "epoch": 3.228637413394919, "grad_norm": 1.123819351196289, "learning_rate": 5.453315416275481e-06, "loss": 0.1133, "step": 6990 }, { "epoch": 3.233256351039261, "grad_norm": 1.2006902694702148, "learning_rate": 5.390650102503184e-06, "loss": 0.1239, "step": 7000 }, { "epoch": 3.2378752886836026, "grad_norm": 1.0388902425765991, "learning_rate": 5.328303385634264e-06, "loss": 0.1136, "step": 7010 }, { "epoch": 3.2424942263279446, "grad_norm": 1.2168902158737183, "learning_rate": 5.266276278627919e-06, "loss": 0.1139, "step": 7020 }, { "epoch": 3.2471131639722866, "grad_norm": 1.59237802028656, "learning_rate": 5.204569789250546e-06, "loss": 0.1028, "step": 7030 }, { "epoch": 3.251732101616628, "grad_norm": 1.5639748573303223, "learning_rate": 5.143184920059429e-06, "loss": 0.1097, "step": 7040 }, { "epoch": 3.25635103926097, "grad_norm": 2.0013725757598877, "learning_rate": 5.082122668386427e-06, "loss": 0.1146, "step": 7050 }, { "epoch": 3.2609699769053115, "grad_norm": 0.9571440815925598, "learning_rate": 5.021384026321757e-06, "loss": 0.1203, "step": 7060 }, { "epoch": 3.2655889145496535, "grad_norm": 1.4330164194107056, "learning_rate": 4.960969980697883e-06, "loss": 0.122, "step": 7070 }, { "epoch": 3.2702078521939955, "grad_norm": 1.023180365562439, "learning_rate": 4.90088151307351e-06, "loss": 0.1053, "step": 7080 }, { "epoch": 3.274826789838337, "grad_norm": 1.043691873550415, "learning_rate": 4.841119599717594e-06, "loss": 0.1197, "step": 7090 }, { "epoch": 3.279445727482679, "grad_norm": 2.174398183822632, "learning_rate": 4.781685211593523e-06, "loss": 0.1017, "step": 7100 }, { "epoch": 3.284064665127021, "grad_norm": 1.0241092443466187, "learning_rate": 4.722579314343292e-06, "loss": 0.1108, "step": 7110 }, { "epoch": 3.2886836027713624, "grad_norm": 1.0809423923492432, "learning_rate": 4.663802868271852e-06, "loss": 0.1274, "step": 7120 }, { "epoch": 3.2933025404157044, "grad_norm": 1.1108380556106567, "learning_rate": 4.605356828331511e-06, "loss": 0.1037, "step": 7130 }, { "epoch": 3.2979214780600463, "grad_norm": 1.2226618528366089, "learning_rate": 4.547242144106381e-06, "loss": 0.1125, "step": 7140 }, { "epoch": 3.302540415704388, "grad_norm": 0.7767813205718994, "learning_rate": 4.489459759796988e-06, "loss": 0.1108, "step": 7150 }, { "epoch": 3.30715935334873, "grad_norm": 0.7558187246322632, "learning_rate": 4.432010614204926e-06, "loss": 0.1074, "step": 7160 }, { "epoch": 3.3117782909930717, "grad_norm": 2.3390016555786133, "learning_rate": 4.374895640717569e-06, "loss": 0.1169, "step": 7170 }, { "epoch": 3.3163972286374133, "grad_norm": 1.1599560976028442, "learning_rate": 4.318115767292958e-06, "loss": 0.1181, "step": 7180 }, { "epoch": 3.321016166281755, "grad_norm": 1.395606517791748, "learning_rate": 4.261671916444679e-06, "loss": 0.1279, "step": 7190 }, { "epoch": 3.325635103926097, "grad_norm": 1.2402153015136719, "learning_rate": 4.2055650052269e-06, "loss": 0.1212, "step": 7200 }, { "epoch": 3.3302540415704387, "grad_norm": 1.0231423377990723, "learning_rate": 4.149795945219476e-06, "loss": 0.1183, "step": 7210 }, { "epoch": 3.3348729792147807, "grad_norm": 1.294407844543457, "learning_rate": 4.0943656425131095e-06, "loss": 0.1154, "step": 7220 }, { "epoch": 3.3394919168591226, "grad_norm": 0.7527818083763123, "learning_rate": 4.03927499769467e-06, "loss": 0.1354, "step": 7230 }, { "epoch": 3.344110854503464, "grad_norm": 0.7987797260284424, "learning_rate": 3.9845249058325205e-06, "loss": 0.099, "step": 7240 }, { "epoch": 3.348729792147806, "grad_norm": 1.1986604928970337, "learning_rate": 3.930116256461997e-06, "loss": 0.1104, "step": 7250 }, { "epoch": 3.353348729792148, "grad_norm": 1.080979347229004, "learning_rate": 3.876049933570966e-06, "loss": 0.1251, "step": 7260 }, { "epoch": 3.3579676674364896, "grad_norm": 0.7739744782447815, "learning_rate": 3.822326815585428e-06, "loss": 0.1338, "step": 7270 }, { "epoch": 3.3625866050808315, "grad_norm": 0.9185677766799927, "learning_rate": 3.7689477753552916e-06, "loss": 0.0994, "step": 7280 }, { "epoch": 3.367205542725173, "grad_norm": 0.8677369356155396, "learning_rate": 3.715913680140154e-06, "loss": 0.1108, "step": 7290 }, { "epoch": 3.371824480369515, "grad_norm": 0.6902599334716797, "learning_rate": 3.663225391595218e-06, "loss": 0.118, "step": 7300 }, { "epoch": 3.376443418013857, "grad_norm": 0.8765599131584167, "learning_rate": 3.6108837657573198e-06, "loss": 0.1069, "step": 7310 }, { "epoch": 3.3810623556581985, "grad_norm": 1.997330665588379, "learning_rate": 3.558889653030975e-06, "loss": 0.1191, "step": 7320 }, { "epoch": 3.3856812933025404, "grad_norm": 0.8299709558486938, "learning_rate": 3.507243898174592e-06, "loss": 0.0935, "step": 7330 }, { "epoch": 3.3903002309468824, "grad_norm": 1.2483935356140137, "learning_rate": 3.455947340286761e-06, "loss": 0.1035, "step": 7340 }, { "epoch": 3.394919168591224, "grad_norm": 0.8822041749954224, "learning_rate": 3.405000812792572e-06, "loss": 0.1104, "step": 7350 }, { "epoch": 3.399538106235566, "grad_norm": 0.9985661506652832, "learning_rate": 3.3544051434301336e-06, "loss": 0.1117, "step": 7360 }, { "epoch": 3.404157043879908, "grad_norm": 1.107095718383789, "learning_rate": 3.3041611542370705e-06, "loss": 0.1204, "step": 7370 }, { "epoch": 3.4087759815242493, "grad_norm": 0.9767152667045593, "learning_rate": 3.2542696615371987e-06, "loss": 0.1054, "step": 7380 }, { "epoch": 3.4133949191685913, "grad_norm": 1.4091322422027588, "learning_rate": 3.2047314759272583e-06, "loss": 0.1135, "step": 7390 }, { "epoch": 3.418013856812933, "grad_norm": 1.990733027458191, "learning_rate": 3.1555474022637448e-06, "loss": 0.123, "step": 7400 }, { "epoch": 3.4226327944572748, "grad_norm": 0.9695513248443604, "learning_rate": 3.1067182396498166e-06, "loss": 0.1158, "step": 7410 }, { "epoch": 3.4272517321016167, "grad_norm": 1.2038146257400513, "learning_rate": 3.05824478142234e-06, "loss": 0.1064, "step": 7420 }, { "epoch": 3.4318706697459582, "grad_norm": 1.2758411169052124, "learning_rate": 3.010127815138958e-06, "loss": 0.1032, "step": 7430 }, { "epoch": 3.4364896073903, "grad_norm": 1.1422789096832275, "learning_rate": 2.962368122565351e-06, "loss": 0.1121, "step": 7440 }, { "epoch": 3.441108545034642, "grad_norm": 0.9431203007698059, "learning_rate": 2.9149664796624815e-06, "loss": 0.1208, "step": 7450 }, { "epoch": 3.4457274826789837, "grad_norm": 0.9915385246276855, "learning_rate": 2.867923656574012e-06, "loss": 0.131, "step": 7460 }, { "epoch": 3.4503464203233256, "grad_norm": 1.3774715662002563, "learning_rate": 2.8212404176138017e-06, "loss": 0.1318, "step": 7470 }, { "epoch": 3.4549653579676676, "grad_norm": 1.2223650217056274, "learning_rate": 2.7749175212534672e-06, "loss": 0.1202, "step": 7480 }, { "epoch": 3.459584295612009, "grad_norm": 0.9574389457702637, "learning_rate": 2.728955720110077e-06, "loss": 0.1133, "step": 7490 }, { "epoch": 3.464203233256351, "grad_norm": 1.1951732635498047, "learning_rate": 2.6833557609339005e-06, "loss": 0.1129, "step": 7500 }, { "epoch": 3.468822170900693, "grad_norm": 1.0490080118179321, "learning_rate": 2.6381183845963137e-06, "loss": 0.1166, "step": 7510 }, { "epoch": 3.4734411085450345, "grad_norm": 1.207564115524292, "learning_rate": 2.5932443260777124e-06, "loss": 0.12, "step": 7520 }, { "epoch": 3.4780600461893765, "grad_norm": 1.182969093322754, "learning_rate": 2.5487343144556254e-06, "loss": 0.1178, "step": 7530 }, { "epoch": 3.4826789838337184, "grad_norm": 1.1554640531539917, "learning_rate": 2.504589072892813e-06, "loss": 0.119, "step": 7540 }, { "epoch": 3.48729792147806, "grad_norm": 1.048616886138916, "learning_rate": 2.4608093186255706e-06, "loss": 0.1056, "step": 7550 }, { "epoch": 3.491916859122402, "grad_norm": 2.8147995471954346, "learning_rate": 2.417395762952032e-06, "loss": 0.1184, "step": 7560 }, { "epoch": 3.496535796766744, "grad_norm": 1.1347233057022095, "learning_rate": 2.3743491112206472e-06, "loss": 0.1171, "step": 7570 }, { "epoch": 3.5011547344110854, "grad_norm": 1.3972876071929932, "learning_rate": 2.3316700628186943e-06, "loss": 0.1068, "step": 7580 }, { "epoch": 3.5057736720554273, "grad_norm": 1.024652361869812, "learning_rate": 2.2893593111609324e-06, "loss": 0.1066, "step": 7590 }, { "epoch": 3.5103926096997693, "grad_norm": 0.6719343662261963, "learning_rate": 2.2474175436783375e-06, "loss": 0.1129, "step": 7600 }, { "epoch": 3.515011547344111, "grad_norm": 1.1656312942504883, "learning_rate": 2.2058454418069167e-06, "loss": 0.1303, "step": 7610 }, { "epoch": 3.5196304849884528, "grad_norm": 1.0880120992660522, "learning_rate": 2.1646436809766663e-06, "loss": 0.101, "step": 7620 }, { "epoch": 3.5242494226327947, "grad_norm": 1.7667478322982788, "learning_rate": 2.1238129306005603e-06, "loss": 0.1146, "step": 7630 }, { "epoch": 3.5288683602771362, "grad_norm": 1.0697081089019775, "learning_rate": 2.083353854063708e-06, "loss": 0.1286, "step": 7640 }, { "epoch": 3.533487297921478, "grad_norm": 1.0240306854248047, "learning_rate": 2.04326710871256e-06, "loss": 0.1053, "step": 7650 }, { "epoch": 3.5381062355658197, "grad_norm": 1.0335919857025146, "learning_rate": 2.0035533458442253e-06, "loss": 0.1226, "step": 7660 }, { "epoch": 3.5427251732101617, "grad_norm": 1.3630998134613037, "learning_rate": 1.9642132106958867e-06, "loss": 0.1168, "step": 7670 }, { "epoch": 3.5473441108545036, "grad_norm": 1.3503059148788452, "learning_rate": 1.92524734243435e-06, "loss": 0.1142, "step": 7680 }, { "epoch": 3.551963048498845, "grad_norm": 1.33393132686615, "learning_rate": 1.8866563741456067e-06, "loss": 0.107, "step": 7690 }, { "epoch": 3.556581986143187, "grad_norm": 0.9496337175369263, "learning_rate": 1.8484409328245967e-06, "loss": 0.1253, "step": 7700 }, { "epoch": 3.5612009237875286, "grad_norm": 1.3230987787246704, "learning_rate": 1.8106016393649895e-06, "loss": 0.1237, "step": 7710 }, { "epoch": 3.5658198614318706, "grad_norm": 1.4718824625015259, "learning_rate": 1.7731391085491046e-06, "loss": 0.1013, "step": 7720 }, { "epoch": 3.5704387990762125, "grad_norm": 0.7922006845474243, "learning_rate": 1.7360539490379413e-06, "loss": 0.1015, "step": 7730 }, { "epoch": 3.575057736720554, "grad_norm": 1.1176987886428833, "learning_rate": 1.6993467633612565e-06, "loss": 0.1089, "step": 7740 }, { "epoch": 3.579676674364896, "grad_norm": 0.9843287467956543, "learning_rate": 1.6630181479078049e-06, "loss": 0.1147, "step": 7750 }, { "epoch": 3.584295612009238, "grad_norm": 1.1108067035675049, "learning_rate": 1.6270686929156314e-06, "loss": 0.1195, "step": 7760 }, { "epoch": 3.5889145496535795, "grad_norm": 1.359505295753479, "learning_rate": 1.5914989824624887e-06, "loss": 0.1171, "step": 7770 }, { "epoch": 3.5935334872979214, "grad_norm": 1.3623625040054321, "learning_rate": 1.5563095944563567e-06, "loss": 0.1124, "step": 7780 }, { "epoch": 3.5981524249422634, "grad_norm": 0.9865480661392212, "learning_rate": 1.5215011006260244e-06, "loss": 0.1159, "step": 7790 }, { "epoch": 3.602771362586605, "grad_norm": 1.2243385314941406, "learning_rate": 1.487074066511826e-06, "loss": 0.1239, "step": 7800 }, { "epoch": 3.607390300230947, "grad_norm": 0.9406094551086426, "learning_rate": 1.4530290514564588e-06, "loss": 0.1207, "step": 7810 }, { "epoch": 3.612009237875289, "grad_norm": 1.0727794170379639, "learning_rate": 1.4193666085958624e-06, "loss": 0.114, "step": 7820 }, { "epoch": 3.6166281755196303, "grad_norm": 0.8868185877799988, "learning_rate": 1.3860872848502682e-06, "loss": 0.1053, "step": 7830 }, { "epoch": 3.6212471131639723, "grad_norm": 0.9300138354301453, "learning_rate": 1.3531916209152895e-06, "loss": 0.1045, "step": 7840 }, { "epoch": 3.6258660508083143, "grad_norm": 1.0008172988891602, "learning_rate": 1.3206801512531396e-06, "loss": 0.1097, "step": 7850 }, { "epoch": 3.6304849884526558, "grad_norm": 0.714224636554718, "learning_rate": 1.2885534040839698e-06, "loss": 0.1089, "step": 7860 }, { "epoch": 3.6351039260969977, "grad_norm": 1.198639988899231, "learning_rate": 1.2568119013772471e-06, "loss": 0.1057, "step": 7870 }, { "epoch": 3.6397228637413397, "grad_norm": 1.3366320133209229, "learning_rate": 1.2254561588433189e-06, "loss": 0.1144, "step": 7880 }, { "epoch": 3.644341801385681, "grad_norm": 1.2186505794525146, "learning_rate": 1.194486685925006e-06, "loss": 0.1169, "step": 7890 }, { "epoch": 3.648960739030023, "grad_norm": 0.9950705766677856, "learning_rate": 1.1639039857893192e-06, "loss": 0.1302, "step": 7900 }, { "epoch": 3.653579676674365, "grad_norm": 1.0247437953948975, "learning_rate": 1.1337085553193156e-06, "loss": 0.1138, "step": 7910 }, { "epoch": 3.6581986143187066, "grad_norm": 1.2590597867965698, "learning_rate": 1.1039008851059963e-06, "loss": 0.1255, "step": 7920 }, { "epoch": 3.6628175519630486, "grad_norm": 1.079540729522705, "learning_rate": 1.0744814594403462e-06, "loss": 0.1274, "step": 7930 }, { "epoch": 3.6674364896073905, "grad_norm": 1.481247067451477, "learning_rate": 1.0454507563054745e-06, "loss": 0.1353, "step": 7940 }, { "epoch": 3.672055427251732, "grad_norm": 1.295339822769165, "learning_rate": 1.0168092473688245e-06, "loss": 0.1143, "step": 7950 }, { "epoch": 3.676674364896074, "grad_norm": 1.4055421352386475, "learning_rate": 9.88557397974546e-07, "loss": 0.1233, "step": 7960 }, { "epoch": 3.681293302540416, "grad_norm": 0.7458164691925049, "learning_rate": 9.606956671358997e-07, "loss": 0.1111, "step": 7970 }, { "epoch": 3.6859122401847575, "grad_norm": 1.3019957542419434, "learning_rate": 9.332245075278162e-07, "loss": 0.1134, "step": 7980 }, { "epoch": 3.6905311778290995, "grad_norm": 1.051591157913208, "learning_rate": 9.061443654795498e-07, "loss": 0.1182, "step": 7990 }, { "epoch": 3.695150115473441, "grad_norm": 1.1991329193115234, "learning_rate": 8.794556809674087e-07, "loss": 0.1244, "step": 8000 }, { "epoch": 3.699769053117783, "grad_norm": 1.3880670070648193, "learning_rate": 8.531588876076108e-07, "loss": 0.1286, "step": 8010 }, { "epoch": 3.7043879907621244, "grad_norm": 0.8209711313247681, "learning_rate": 8.272544126492532e-07, "loss": 0.1112, "step": 8020 }, { "epoch": 3.7090069284064664, "grad_norm": 1.2587535381317139, "learning_rate": 8.017426769673514e-07, "loss": 0.1053, "step": 8030 }, { "epoch": 3.7136258660508084, "grad_norm": 1.401945948600769, "learning_rate": 7.766240950560167e-07, "loss": 0.1185, "step": 8040 }, { "epoch": 3.71824480369515, "grad_norm": 1.0820854902267456, "learning_rate": 7.518990750217058e-07, "loss": 0.126, "step": 8050 }, { "epoch": 3.722863741339492, "grad_norm": 1.4345390796661377, "learning_rate": 7.275680185766132e-07, "loss": 0.1179, "step": 8060 }, { "epoch": 3.727482678983834, "grad_norm": 1.3209582567214966, "learning_rate": 7.036313210321166e-07, "loss": 0.1194, "step": 8070 }, { "epoch": 3.7321016166281753, "grad_norm": 0.7082709074020386, "learning_rate": 6.800893712923723e-07, "loss": 0.1255, "step": 8080 }, { "epoch": 3.7367205542725173, "grad_norm": 2.2187857627868652, "learning_rate": 6.569425518479999e-07, "loss": 0.1284, "step": 8090 }, { "epoch": 3.741339491916859, "grad_norm": 2.4308388233184814, "learning_rate": 6.341912387698546e-07, "loss": 0.1257, "step": 8100 }, { "epoch": 3.7459584295612007, "grad_norm": 1.1213014125823975, "learning_rate": 6.118358017029175e-07, "loss": 0.1179, "step": 8110 }, { "epoch": 3.7505773672055427, "grad_norm": 1.8573155403137207, "learning_rate": 5.898766038603093e-07, "loss": 0.12, "step": 8120 }, { "epoch": 3.7551963048498846, "grad_norm": 1.237615704536438, "learning_rate": 5.683140020173616e-07, "loss": 0.1082, "step": 8130 }, { "epoch": 3.759815242494226, "grad_norm": 1.0821892023086548, "learning_rate": 5.471483465058463e-07, "loss": 0.0956, "step": 8140 }, { "epoch": 3.764434180138568, "grad_norm": 1.0301852226257324, "learning_rate": 5.263799812082637e-07, "loss": 0.1136, "step": 8150 }, { "epoch": 3.76905311778291, "grad_norm": 1.125071406364441, "learning_rate": 5.060092435522607e-07, "loss": 0.1005, "step": 8160 }, { "epoch": 3.7736720554272516, "grad_norm": 1.371978998184204, "learning_rate": 4.860364645051602e-07, "loss": 0.1059, "step": 8170 }, { "epoch": 3.7782909930715936, "grad_norm": 3.297619342803955, "learning_rate": 4.664619685685656e-07, "loss": 0.1245, "step": 8180 }, { "epoch": 3.7829099307159355, "grad_norm": 1.1489087343215942, "learning_rate": 4.4728607377310383e-07, "loss": 0.1069, "step": 8190 }, { "epoch": 3.787528868360277, "grad_norm": 0.9412850737571716, "learning_rate": 4.2850909167324873e-07, "loss": 0.109, "step": 8200 }, { "epoch": 3.792147806004619, "grad_norm": 0.9904099702835083, "learning_rate": 4.1013132734225857e-07, "loss": 0.0977, "step": 8210 }, { "epoch": 3.796766743648961, "grad_norm": 2.041278600692749, "learning_rate": 3.921530793672329e-07, "loss": 0.1209, "step": 8220 }, { "epoch": 3.8013856812933025, "grad_norm": 1.0898220539093018, "learning_rate": 3.745746398442468e-07, "loss": 0.1171, "step": 8230 }, { "epoch": 3.8060046189376444, "grad_norm": 0.9231056571006775, "learning_rate": 3.5739629437360475e-07, "loss": 0.1179, "step": 8240 }, { "epoch": 3.8106235565819864, "grad_norm": 1.1029608249664307, "learning_rate": 3.406183220552167e-07, "loss": 0.1231, "step": 8250 }, { "epoch": 3.815242494226328, "grad_norm": 1.0381815433502197, "learning_rate": 3.242409954840403e-07, "loss": 0.1369, "step": 8260 }, { "epoch": 3.81986143187067, "grad_norm": 0.8414006233215332, "learning_rate": 3.082645807456763e-07, "loss": 0.1167, "step": 8270 }, { "epoch": 3.824480369515012, "grad_norm": 1.3984060287475586, "learning_rate": 2.9268933741202487e-07, "loss": 0.1199, "step": 8280 }, { "epoch": 3.8290993071593533, "grad_norm": 1.1790199279785156, "learning_rate": 2.775155185370776e-07, "loss": 0.1225, "step": 8290 }, { "epoch": 3.8337182448036953, "grad_norm": 0.9131882190704346, "learning_rate": 2.6274337065280986e-07, "loss": 0.1097, "step": 8300 }, { "epoch": 3.838337182448037, "grad_norm": 1.096301794052124, "learning_rate": 2.483731337651618e-07, "loss": 0.1087, "step": 8310 }, { "epoch": 3.8429561200923787, "grad_norm": 1.149127721786499, "learning_rate": 2.3440504135016083e-07, "loss": 0.1197, "step": 8320 }, { "epoch": 3.8475750577367207, "grad_norm": 1.1328707933425903, "learning_rate": 2.2083932035010802e-07, "loss": 0.1203, "step": 8330 }, { "epoch": 3.852193995381062, "grad_norm": 0.8107655644416809, "learning_rate": 2.0767619116988934e-07, "loss": 0.115, "step": 8340 }, { "epoch": 3.856812933025404, "grad_norm": 1.0737303495407104, "learning_rate": 1.9491586767342308e-07, "loss": 0.1042, "step": 8350 }, { "epoch": 3.8614318706697457, "grad_norm": 1.760962724685669, "learning_rate": 1.8255855718014858e-07, "loss": 0.0973, "step": 8360 }, { "epoch": 3.8660508083140877, "grad_norm": 1.6400498151779175, "learning_rate": 1.7060446046168188e-07, "loss": 0.1177, "step": 8370 }, { "epoch": 3.8706697459584296, "grad_norm": 1.1925407648086548, "learning_rate": 1.5905377173854873e-07, "loss": 0.1223, "step": 8380 }, { "epoch": 3.875288683602771, "grad_norm": 1.2444329261779785, "learning_rate": 1.4790667867702335e-07, "loss": 0.1139, "step": 8390 }, { "epoch": 3.879907621247113, "grad_norm": 1.1802165508270264, "learning_rate": 1.371633623860835e-07, "loss": 0.1099, "step": 8400 }, { "epoch": 3.884526558891455, "grad_norm": 0.9776859283447266, "learning_rate": 1.268239974144686e-07, "loss": 0.1092, "step": 8410 }, { "epoch": 3.8891454965357966, "grad_norm": 1.4018887281417847, "learning_rate": 1.1688875174784563e-07, "loss": 0.1172, "step": 8420 }, { "epoch": 3.8937644341801385, "grad_norm": 1.2019463777542114, "learning_rate": 1.073577868060699e-07, "loss": 0.1071, "step": 8430 }, { "epoch": 3.8983833718244805, "grad_norm": 1.0367040634155273, "learning_rate": 9.823125744057582e-08, "loss": 0.125, "step": 8440 }, { "epoch": 3.903002309468822, "grad_norm": 0.9557856321334839, "learning_rate": 8.950931193185131e-08, "loss": 0.1088, "step": 8450 }, { "epoch": 3.907621247113164, "grad_norm": 1.0708262920379639, "learning_rate": 8.119209198703682e-08, "loss": 0.1196, "step": 8460 }, { "epoch": 3.912240184757506, "grad_norm": 1.1957937479019165, "learning_rate": 7.32797327376078e-08, "loss": 0.1306, "step": 8470 }, { "epoch": 3.9168591224018474, "grad_norm": 0.9860221743583679, "learning_rate": 6.577236273720145e-08, "loss": 0.1138, "step": 8480 }, { "epoch": 3.9214780600461894, "grad_norm": 0.8725905418395996, "learning_rate": 5.867010395951278e-08, "loss": 0.11, "step": 8490 }, { "epoch": 3.9260969976905313, "grad_norm": 0.9754180908203125, "learning_rate": 5.197307179631017e-08, "loss": 0.1127, "step": 8500 } ], "logging_steps": 10, "max_steps": 8660, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.338136638800003e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }