| { |
| "best_metric": 0.2809600234031677, |
| "best_model_checkpoint": "./lora_bn_resume/checkpoint-1800", |
| "epoch": 1.157556270096463, |
| "eval_steps": 200, |
| "global_step": 1800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006430868167202572, |
| "grad_norm": 0.3332834541797638, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 0.643, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.012861736334405145, |
| "grad_norm": 0.3670434355735779, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.5391, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01929260450160772, |
| "grad_norm": 0.2655458152294159, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.4222, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.02572347266881029, |
| "grad_norm": 0.18765214085578918, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.38, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.03215434083601286, |
| "grad_norm": 0.17279677093029022, |
| "learning_rate": 0.00015, |
| "loss": 0.3474, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03858520900321544, |
| "grad_norm": 0.19536016881465912, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.3482, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.04501607717041801, |
| "grad_norm": 0.24155691266059875, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 0.3519, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.05144694533762058, |
| "grad_norm": 0.15769515931606293, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.3442, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05787781350482315, |
| "grad_norm": 0.15895752608776093, |
| "learning_rate": 0.00027, |
| "loss": 0.3419, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.06430868167202572, |
| "grad_norm": 0.1517348736524582, |
| "learning_rate": 0.0003, |
| "loss": 0.3325, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0707395498392283, |
| "grad_norm": 0.1374281644821167, |
| "learning_rate": 0.00029934282584884994, |
| "loss": 0.3364, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.07717041800643087, |
| "grad_norm": 0.14599083364009857, |
| "learning_rate": 0.00029868565169769985, |
| "loss": 0.3296, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.08360128617363344, |
| "grad_norm": 0.1735353320837021, |
| "learning_rate": 0.0002980284775465498, |
| "loss": 0.3296, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.09003215434083602, |
| "grad_norm": 0.16351208090782166, |
| "learning_rate": 0.00029737130339539973, |
| "loss": 0.3359, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.09646302250803858, |
| "grad_norm": 0.15383951365947723, |
| "learning_rate": 0.0002967141292442497, |
| "loss": 0.3401, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.10289389067524116, |
| "grad_norm": 0.16704361140727997, |
| "learning_rate": 0.00029605695509309966, |
| "loss": 0.3378, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10932475884244373, |
| "grad_norm": 0.14677385985851288, |
| "learning_rate": 0.00029539978094194957, |
| "loss": 0.3404, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.1157556270096463, |
| "grad_norm": 0.2054668664932251, |
| "learning_rate": 0.00029474260679079954, |
| "loss": 0.3379, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.12218649517684887, |
| "grad_norm": 0.15476278960704803, |
| "learning_rate": 0.00029408543263964945, |
| "loss": 0.3395, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.12861736334405144, |
| "grad_norm": 0.1571033000946045, |
| "learning_rate": 0.0002934282584884994, |
| "loss": 0.3318, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12861736334405144, |
| "eval_loss": 0.32538482546806335, |
| "eval_runtime": 830.7418, |
| "eval_samples_per_second": 2.407, |
| "eval_steps_per_second": 2.407, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.13504823151125403, |
| "grad_norm": 0.13506701588630676, |
| "learning_rate": 0.0002927710843373494, |
| "loss": 0.3316, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.1414790996784566, |
| "grad_norm": 0.16322733461856842, |
| "learning_rate": 0.0002921139101861993, |
| "loss": 0.3415, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.14790996784565916, |
| "grad_norm": 0.16979773342609406, |
| "learning_rate": 0.00029145673603504926, |
| "loss": 0.3272, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.15434083601286175, |
| "grad_norm": 0.1605272740125656, |
| "learning_rate": 0.0002907995618838992, |
| "loss": 0.3292, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.1607717041800643, |
| "grad_norm": 0.16240820288658142, |
| "learning_rate": 0.00029014238773274913, |
| "loss": 0.3256, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.16720257234726688, |
| "grad_norm": 0.14710214734077454, |
| "learning_rate": 0.0002894852135815991, |
| "loss": 0.3234, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.17363344051446947, |
| "grad_norm": 0.14770746231079102, |
| "learning_rate": 0.000288828039430449, |
| "loss": 0.3264, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.18006430868167203, |
| "grad_norm": 0.14894965291023254, |
| "learning_rate": 0.000288170865279299, |
| "loss": 0.3211, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.1864951768488746, |
| "grad_norm": 0.1738394796848297, |
| "learning_rate": 0.00028751369112814894, |
| "loss": 0.3107, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.19292604501607716, |
| "grad_norm": 0.15344616770744324, |
| "learning_rate": 0.00028685651697699885, |
| "loss": 0.3126, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.19935691318327975, |
| "grad_norm": 0.180983766913414, |
| "learning_rate": 0.0002861993428258488, |
| "loss": 0.3142, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.2057877813504823, |
| "grad_norm": 0.17168308794498444, |
| "learning_rate": 0.00028554216867469873, |
| "loss": 0.3207, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.21221864951768488, |
| "grad_norm": 0.17984597384929657, |
| "learning_rate": 0.0002848849945235487, |
| "loss": 0.3158, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.21864951768488747, |
| "grad_norm": 0.15579424798488617, |
| "learning_rate": 0.00028422782037239866, |
| "loss": 0.3133, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.22508038585209003, |
| "grad_norm": 0.15541236102581024, |
| "learning_rate": 0.0002835706462212486, |
| "loss": 0.3203, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.2315112540192926, |
| "grad_norm": 0.14372068643569946, |
| "learning_rate": 0.00028291347207009854, |
| "loss": 0.3284, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.2379421221864952, |
| "grad_norm": 0.16621021926403046, |
| "learning_rate": 0.0002822562979189485, |
| "loss": 0.3218, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.24437299035369775, |
| "grad_norm": 0.1540420651435852, |
| "learning_rate": 0.0002815991237677984, |
| "loss": 0.3117, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.2508038585209003, |
| "grad_norm": 0.1495533287525177, |
| "learning_rate": 0.0002809419496166484, |
| "loss": 0.318, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.2572347266881029, |
| "grad_norm": 0.3620932400226593, |
| "learning_rate": 0.00028028477546549835, |
| "loss": 0.3241, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2572347266881029, |
| "eval_loss": 0.3119981288909912, |
| "eval_runtime": 842.192, |
| "eval_samples_per_second": 2.375, |
| "eval_steps_per_second": 2.375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.26366559485530544, |
| "grad_norm": 0.14988340437412262, |
| "learning_rate": 0.00027962760131434826, |
| "loss": 0.3132, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.27009646302250806, |
| "grad_norm": 0.14897547662258148, |
| "learning_rate": 0.0002789704271631982, |
| "loss": 0.3159, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.2765273311897106, |
| "grad_norm": 0.1518355906009674, |
| "learning_rate": 0.0002783132530120482, |
| "loss": 0.3131, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.2829581993569132, |
| "grad_norm": 0.1667843610048294, |
| "learning_rate": 0.0002776560788608981, |
| "loss": 0.3176, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.28938906752411575, |
| "grad_norm": 0.1573045551776886, |
| "learning_rate": 0.00027699890470974807, |
| "loss": 0.3063, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.2958199356913183, |
| "grad_norm": 0.2083781659603119, |
| "learning_rate": 0.000276341730558598, |
| "loss": 0.3121, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.3022508038585209, |
| "grad_norm": 0.15114179253578186, |
| "learning_rate": 0.00027568455640744795, |
| "loss": 0.3115, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.3086816720257235, |
| "grad_norm": 0.1676609367132187, |
| "learning_rate": 0.0002750273822562979, |
| "loss": 0.3102, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.31511254019292606, |
| "grad_norm": 0.1511840969324112, |
| "learning_rate": 0.0002743702081051478, |
| "loss": 0.2958, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.3215434083601286, |
| "grad_norm": 0.14467953145503998, |
| "learning_rate": 0.0002737130339539978, |
| "loss": 0.3141, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3279742765273312, |
| "grad_norm": 0.14991098642349243, |
| "learning_rate": 0.00027305585980284776, |
| "loss": 0.2971, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.33440514469453375, |
| "grad_norm": 0.15232595801353455, |
| "learning_rate": 0.00027239868565169767, |
| "loss": 0.309, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.3408360128617363, |
| "grad_norm": 0.14672474563121796, |
| "learning_rate": 0.00027174151150054763, |
| "loss": 0.303, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.34726688102893893, |
| "grad_norm": 0.1486695259809494, |
| "learning_rate": 0.0002710843373493976, |
| "loss": 0.3049, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.3536977491961415, |
| "grad_norm": 0.14715538918972015, |
| "learning_rate": 0.0002704271631982475, |
| "loss": 0.2989, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.36012861736334406, |
| "grad_norm": 0.16407349705696106, |
| "learning_rate": 0.0002697699890470975, |
| "loss": 0.3096, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.3665594855305466, |
| "grad_norm": 0.17212547361850739, |
| "learning_rate": 0.00026911281489594744, |
| "loss": 0.3071, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.3729903536977492, |
| "grad_norm": 0.17516419291496277, |
| "learning_rate": 0.00026845564074479735, |
| "loss": 0.3012, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.37942122186495175, |
| "grad_norm": 0.16375690698623657, |
| "learning_rate": 0.0002677984665936473, |
| "loss": 0.3001, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.3858520900321543, |
| "grad_norm": 0.16078205406665802, |
| "learning_rate": 0.00026714129244249723, |
| "loss": 0.3033, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3858520900321543, |
| "eval_loss": 0.30340561270713806, |
| "eval_runtime": 843.3627, |
| "eval_samples_per_second": 2.371, |
| "eval_steps_per_second": 2.371, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.39228295819935693, |
| "grad_norm": 0.16159534454345703, |
| "learning_rate": 0.0002664841182913472, |
| "loss": 0.3094, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.3987138263665595, |
| "grad_norm": 0.16596971452236176, |
| "learning_rate": 0.00026582694414019716, |
| "loss": 0.3006, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.40514469453376206, |
| "grad_norm": 0.1850331723690033, |
| "learning_rate": 0.00026516976998904707, |
| "loss": 0.3071, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.4115755627009646, |
| "grad_norm": 0.16145645081996918, |
| "learning_rate": 0.00026451259583789704, |
| "loss": 0.3045, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.4180064308681672, |
| "grad_norm": 0.1462334543466568, |
| "learning_rate": 0.00026385542168674695, |
| "loss": 0.3127, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.42443729903536975, |
| "grad_norm": 0.1508970707654953, |
| "learning_rate": 0.0002631982475355969, |
| "loss": 0.3047, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.43086816720257237, |
| "grad_norm": 0.17199252545833588, |
| "learning_rate": 0.0002625410733844469, |
| "loss": 0.304, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.43729903536977494, |
| "grad_norm": 0.15578508377075195, |
| "learning_rate": 0.0002618838992332968, |
| "loss": 0.3049, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.4437299035369775, |
| "grad_norm": 0.17518927156925201, |
| "learning_rate": 0.00026122672508214676, |
| "loss": 0.2975, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.45016077170418006, |
| "grad_norm": 0.16074487566947937, |
| "learning_rate": 0.0002605695509309967, |
| "loss": 0.2911, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4565916398713826, |
| "grad_norm": 0.13804423809051514, |
| "learning_rate": 0.00025991237677984664, |
| "loss": 0.3013, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.4630225080385852, |
| "grad_norm": 0.15148524940013885, |
| "learning_rate": 0.0002592552026286966, |
| "loss": 0.302, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.4694533762057878, |
| "grad_norm": 0.18637600541114807, |
| "learning_rate": 0.0002585980284775465, |
| "loss": 0.2945, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.4758842443729904, |
| "grad_norm": 0.16151027381420135, |
| "learning_rate": 0.0002579408543263965, |
| "loss": 0.2991, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.48231511254019294, |
| "grad_norm": 0.14255981147289276, |
| "learning_rate": 0.00025728368017524644, |
| "loss": 0.3166, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4887459807073955, |
| "grad_norm": 0.14939677715301514, |
| "learning_rate": 0.00025662650602409636, |
| "loss": 0.296, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.49517684887459806, |
| "grad_norm": 0.15057405829429626, |
| "learning_rate": 0.0002559693318729463, |
| "loss": 0.2827, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.5016077170418006, |
| "grad_norm": 0.162841796875, |
| "learning_rate": 0.00025531215772179623, |
| "loss": 0.301, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.5080385852090032, |
| "grad_norm": 0.13532967865467072, |
| "learning_rate": 0.0002546549835706462, |
| "loss": 0.2915, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.5144694533762058, |
| "grad_norm": 0.14414694905281067, |
| "learning_rate": 0.00025399780941949616, |
| "loss": 0.2963, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5144694533762058, |
| "eval_loss": 0.2967182695865631, |
| "eval_runtime": 836.6673, |
| "eval_samples_per_second": 2.39, |
| "eval_steps_per_second": 2.39, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5209003215434084, |
| "grad_norm": 0.1773417443037033, |
| "learning_rate": 0.0002533406352683461, |
| "loss": 0.2983, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.5273311897106109, |
| "grad_norm": 0.15203996002674103, |
| "learning_rate": 0.00025268346111719604, |
| "loss": 0.3116, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.5337620578778135, |
| "grad_norm": 0.14001955091953278, |
| "learning_rate": 0.00025202628696604595, |
| "loss": 0.2895, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.5401929260450161, |
| "grad_norm": 0.14643649756908417, |
| "learning_rate": 0.0002513691128148959, |
| "loss": 0.2923, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5466237942122186, |
| "grad_norm": 0.1428484320640564, |
| "learning_rate": 0.0002507119386637459, |
| "loss": 0.3001, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5530546623794212, |
| "grad_norm": 0.1566481739282608, |
| "learning_rate": 0.0002500547645125958, |
| "loss": 0.3019, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.5594855305466238, |
| "grad_norm": 0.15484847128391266, |
| "learning_rate": 0.00024939759036144576, |
| "loss": 0.2952, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.5659163987138264, |
| "grad_norm": 0.16524390876293182, |
| "learning_rate": 0.00024874041621029573, |
| "loss": 0.2956, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.572347266881029, |
| "grad_norm": 0.16674397885799408, |
| "learning_rate": 0.00024808324205914564, |
| "loss": 0.2917, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.5787781350482315, |
| "grad_norm": 0.15178845822811127, |
| "learning_rate": 0.0002474260679079956, |
| "loss": 0.2999, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5852090032154341, |
| "grad_norm": 0.15306776762008667, |
| "learning_rate": 0.0002467688937568455, |
| "loss": 0.2909, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.5916398713826366, |
| "grad_norm": 0.16369566321372986, |
| "learning_rate": 0.0002461117196056955, |
| "loss": 0.3041, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.5980707395498392, |
| "grad_norm": 0.15131248533725739, |
| "learning_rate": 0.00024545454545454545, |
| "loss": 0.2948, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.6045016077170418, |
| "grad_norm": 0.1472727656364441, |
| "learning_rate": 0.00024479737130339536, |
| "loss": 0.2926, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.6109324758842444, |
| "grad_norm": 0.17377722263336182, |
| "learning_rate": 0.00024414019715224533, |
| "loss": 0.298, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.617363344051447, |
| "grad_norm": 0.1630556285381317, |
| "learning_rate": 0.00024348302300109526, |
| "loss": 0.2921, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.6237942122186495, |
| "grad_norm": 0.1495707631111145, |
| "learning_rate": 0.0002428258488499452, |
| "loss": 0.3057, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.6302250803858521, |
| "grad_norm": 0.14349451661109924, |
| "learning_rate": 0.00024216867469879517, |
| "loss": 0.2978, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.6366559485530546, |
| "grad_norm": 0.15608881413936615, |
| "learning_rate": 0.0002415115005476451, |
| "loss": 0.2888, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.6430868167202572, |
| "grad_norm": 0.15335732698440552, |
| "learning_rate": 0.00024085432639649505, |
| "loss": 0.2968, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6430868167202572, |
| "eval_loss": 0.2915716767311096, |
| "eval_runtime": 833.5453, |
| "eval_samples_per_second": 2.399, |
| "eval_steps_per_second": 2.399, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6495176848874598, |
| "grad_norm": 0.17396800220012665, |
| "learning_rate": 0.00024019715224534498, |
| "loss": 0.285, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.6559485530546624, |
| "grad_norm": 0.15287892520427704, |
| "learning_rate": 0.00023953997809419495, |
| "loss": 0.2992, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.662379421221865, |
| "grad_norm": 0.15309476852416992, |
| "learning_rate": 0.0002388828039430449, |
| "loss": 0.2927, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.6688102893890675, |
| "grad_norm": 0.17866992950439453, |
| "learning_rate": 0.00023822562979189483, |
| "loss": 0.291, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.6752411575562701, |
| "grad_norm": 0.1827457696199417, |
| "learning_rate": 0.0002375684556407448, |
| "loss": 0.289, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.6816720257234726, |
| "grad_norm": 0.15376009047031403, |
| "learning_rate": 0.0002369112814895947, |
| "loss": 0.2916, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.6881028938906752, |
| "grad_norm": 0.16380611062049866, |
| "learning_rate": 0.00023625410733844467, |
| "loss": 0.2894, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.6945337620578779, |
| "grad_norm": 0.1561112254858017, |
| "learning_rate": 0.00023559693318729464, |
| "loss": 0.2895, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.7009646302250804, |
| "grad_norm": 0.14859697222709656, |
| "learning_rate": 0.00023493975903614455, |
| "loss": 0.2889, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.707395498392283, |
| "grad_norm": 0.15627552568912506, |
| "learning_rate": 0.0002342825848849945, |
| "loss": 0.2889, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.7138263665594855, |
| "grad_norm": 0.16106264293193817, |
| "learning_rate": 0.00023362541073384445, |
| "loss": 0.2858, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.7202572347266881, |
| "grad_norm": 0.1667865663766861, |
| "learning_rate": 0.0002329682365826944, |
| "loss": 0.289, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.7266881028938906, |
| "grad_norm": 0.17265114188194275, |
| "learning_rate": 0.00023231106243154436, |
| "loss": 0.2888, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.7331189710610932, |
| "grad_norm": 0.16795796155929565, |
| "learning_rate": 0.00023165388828039427, |
| "loss": 0.2824, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.7395498392282959, |
| "grad_norm": 0.144576758146286, |
| "learning_rate": 0.00023099671412924423, |
| "loss": 0.2896, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.7459807073954984, |
| "grad_norm": 0.15994594991207123, |
| "learning_rate": 0.0002303395399780942, |
| "loss": 0.2969, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.752411575562701, |
| "grad_norm": 0.1481965035200119, |
| "learning_rate": 0.0002296823658269441, |
| "loss": 0.2832, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.7588424437299035, |
| "grad_norm": 0.143247589468956, |
| "learning_rate": 0.00022902519167579408, |
| "loss": 0.293, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.7652733118971061, |
| "grad_norm": 0.17525409162044525, |
| "learning_rate": 0.000228368017524644, |
| "loss": 0.282, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.7717041800643086, |
| "grad_norm": 0.16322872042655945, |
| "learning_rate": 0.00022771084337349395, |
| "loss": 0.2888, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7717041800643086, |
| "eval_loss": 0.2870965301990509, |
| "eval_runtime": 837.2115, |
| "eval_samples_per_second": 2.389, |
| "eval_steps_per_second": 2.389, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.7781350482315113, |
| "grad_norm": 0.1486148089170456, |
| "learning_rate": 0.00022705366922234392, |
| "loss": 0.2648, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.7845659163987139, |
| "grad_norm": 0.1699255108833313, |
| "learning_rate": 0.00022639649507119383, |
| "loss": 0.2781, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.7909967845659164, |
| "grad_norm": 0.17535263299942017, |
| "learning_rate": 0.0002257393209200438, |
| "loss": 0.258, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.797427652733119, |
| "grad_norm": 0.1789318472146988, |
| "learning_rate": 0.00022508214676889373, |
| "loss": 0.2704, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.8038585209003215, |
| "grad_norm": 0.1452336609363556, |
| "learning_rate": 0.00022442497261774367, |
| "loss": 0.2644, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.8102893890675241, |
| "grad_norm": 0.14961348474025726, |
| "learning_rate": 0.00022376779846659364, |
| "loss": 0.2761, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.8167202572347267, |
| "grad_norm": 0.14857113361358643, |
| "learning_rate": 0.00022311062431544358, |
| "loss": 0.2693, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.8231511254019293, |
| "grad_norm": 0.172617107629776, |
| "learning_rate": 0.00022245345016429352, |
| "loss": 0.2668, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.8295819935691319, |
| "grad_norm": 0.15187814831733704, |
| "learning_rate": 0.00022179627601314345, |
| "loss": 0.2612, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.8360128617363344, |
| "grad_norm": 0.15238122642040253, |
| "learning_rate": 0.0002211391018619934, |
| "loss": 0.281, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.842443729903537, |
| "grad_norm": 0.15372508764266968, |
| "learning_rate": 0.00022048192771084336, |
| "loss": 0.268, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.8488745980707395, |
| "grad_norm": 0.17595216631889343, |
| "learning_rate": 0.0002198247535596933, |
| "loss": 0.2708, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.8553054662379421, |
| "grad_norm": 0.17156840860843658, |
| "learning_rate": 0.00021916757940854324, |
| "loss": 0.2781, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.8617363344051447, |
| "grad_norm": 0.15553158521652222, |
| "learning_rate": 0.0002185104052573932, |
| "loss": 0.2691, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.8681672025723473, |
| "grad_norm": 0.15347564220428467, |
| "learning_rate": 0.00021785323110624314, |
| "loss": 0.2677, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.8745980707395499, |
| "grad_norm": 0.15675435960292816, |
| "learning_rate": 0.00021719605695509308, |
| "loss": 0.2745, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.8810289389067524, |
| "grad_norm": 0.17261667549610138, |
| "learning_rate": 0.00021653888280394302, |
| "loss": 0.2738, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.887459807073955, |
| "grad_norm": 0.17966938018798828, |
| "learning_rate": 0.00021588170865279298, |
| "loss": 0.2626, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.8938906752411575, |
| "grad_norm": 0.1592021882534027, |
| "learning_rate": 0.00021522453450164292, |
| "loss": 0.2714, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.9003215434083601, |
| "grad_norm": 0.203449547290802, |
| "learning_rate": 0.00021456736035049286, |
| "loss": 0.2677, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.9003215434083601, |
| "eval_loss": 0.28547272086143494, |
| "eval_runtime": 841.1547, |
| "eval_samples_per_second": 2.378, |
| "eval_steps_per_second": 2.378, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.9067524115755627, |
| "grad_norm": 0.15531207621097565, |
| "learning_rate": 0.00021391018619934283, |
| "loss": 0.27, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.9131832797427653, |
| "grad_norm": 0.33703845739364624, |
| "learning_rate": 0.00021325301204819274, |
| "loss": 0.2748, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.9196141479099679, |
| "grad_norm": 0.20089037716388702, |
| "learning_rate": 0.0002125958378970427, |
| "loss": 0.2685, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.9260450160771704, |
| "grad_norm": 0.1531943380832672, |
| "learning_rate": 0.00021193866374589267, |
| "loss": 0.2729, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.932475884244373, |
| "grad_norm": 0.15565109252929688, |
| "learning_rate": 0.00021128148959474258, |
| "loss": 0.2681, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.9389067524115756, |
| "grad_norm": 0.18514017760753632, |
| "learning_rate": 0.00021062431544359255, |
| "loss": 0.2761, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.9453376205787781, |
| "grad_norm": 0.16498805582523346, |
| "learning_rate": 0.00020996714129244246, |
| "loss": 0.2723, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.9517684887459807, |
| "grad_norm": 0.16682648658752441, |
| "learning_rate": 0.00020930996714129242, |
| "loss": 0.2679, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.9581993569131833, |
| "grad_norm": 0.16485853493213654, |
| "learning_rate": 0.0002086527929901424, |
| "loss": 0.2649, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.9646302250803859, |
| "grad_norm": 0.28759464621543884, |
| "learning_rate": 0.0002079956188389923, |
| "loss": 0.2761, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9710610932475884, |
| "grad_norm": 0.16720062494277954, |
| "learning_rate": 0.00020733844468784227, |
| "loss": 0.2622, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.977491961414791, |
| "grad_norm": 0.15708176791667938, |
| "learning_rate": 0.00020668127053669218, |
| "loss": 0.2785, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.9839228295819936, |
| "grad_norm": 0.14977172017097473, |
| "learning_rate": 0.00020602409638554214, |
| "loss": 0.2647, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.9903536977491961, |
| "grad_norm": 0.15259595215320587, |
| "learning_rate": 0.0002053669222343921, |
| "loss": 0.2612, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.9967845659163987, |
| "grad_norm": 0.16366101801395416, |
| "learning_rate": 0.00020470974808324202, |
| "loss": 0.2717, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.0032154340836013, |
| "grad_norm": 0.1795603334903717, |
| "learning_rate": 0.000204052573932092, |
| "loss": 0.267, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.0096463022508038, |
| "grad_norm": 0.17623689770698547, |
| "learning_rate": 0.00020339539978094195, |
| "loss": 0.252, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.0160771704180065, |
| "grad_norm": 0.15394379198551178, |
| "learning_rate": 0.00020273822562979186, |
| "loss": 0.2685, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.022508038585209, |
| "grad_norm": 0.16083110868930817, |
| "learning_rate": 0.00020208105147864183, |
| "loss": 0.2573, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.0289389067524115, |
| "grad_norm": 0.1885363757610321, |
| "learning_rate": 0.00020142387732749177, |
| "loss": 0.2592, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.0289389067524115, |
| "eval_loss": 0.2842000424861908, |
| "eval_runtime": 845.1823, |
| "eval_samples_per_second": 2.366, |
| "eval_steps_per_second": 2.366, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.0353697749196142, |
| "grad_norm": 0.1810334175825119, |
| "learning_rate": 0.0002007667031763417, |
| "loss": 0.272, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.0418006430868167, |
| "grad_norm": 0.17008474469184875, |
| "learning_rate": 0.00020010952902519167, |
| "loss": 0.2516, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.0482315112540193, |
| "grad_norm": 0.1848730593919754, |
| "learning_rate": 0.00019945235487404158, |
| "loss": 0.2627, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.0546623794212218, |
| "grad_norm": 0.16504080593585968, |
| "learning_rate": 0.00019879518072289155, |
| "loss": 0.256, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.0610932475884245, |
| "grad_norm": 0.166968435049057, |
| "learning_rate": 0.0001981380065717415, |
| "loss": 0.269, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.067524115755627, |
| "grad_norm": 0.20997032523155212, |
| "learning_rate": 0.00019748083242059143, |
| "loss": 0.2641, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.0739549839228295, |
| "grad_norm": 0.18889103829860687, |
| "learning_rate": 0.0001968236582694414, |
| "loss": 0.2499, |
| "step": 1670 |
| }, |
| { |
| "epoch": 1.0803858520900322, |
| "grad_norm": 0.15986306965351105, |
| "learning_rate": 0.00019616648411829133, |
| "loss": 0.2659, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.0868167202572347, |
| "grad_norm": 0.15300147235393524, |
| "learning_rate": 0.00019550930996714127, |
| "loss": 0.2649, |
| "step": 1690 |
| }, |
| { |
| "epoch": 1.0932475884244373, |
| "grad_norm": 0.16770875453948975, |
| "learning_rate": 0.0001948521358159912, |
| "loss": 0.265, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.09967845659164, |
| "grad_norm": 0.15347127616405487, |
| "learning_rate": 0.00019419496166484117, |
| "loss": 0.2629, |
| "step": 1710 |
| }, |
| { |
| "epoch": 1.1061093247588425, |
| "grad_norm": 0.1624882072210312, |
| "learning_rate": 0.0001935377875136911, |
| "loss": 0.2651, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.112540192926045, |
| "grad_norm": 0.17137973010540009, |
| "learning_rate": 0.00019288061336254105, |
| "loss": 0.2564, |
| "step": 1730 |
| }, |
| { |
| "epoch": 1.1189710610932475, |
| "grad_norm": 0.16637948155403137, |
| "learning_rate": 0.00019222343921139102, |
| "loss": 0.2642, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.1254019292604502, |
| "grad_norm": 0.1559745818376541, |
| "learning_rate": 0.00019156626506024093, |
| "loss": 0.2679, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.1318327974276527, |
| "grad_norm": 0.1712270975112915, |
| "learning_rate": 0.0001909090909090909, |
| "loss": 0.2611, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.1382636655948553, |
| "grad_norm": 0.18316815793514252, |
| "learning_rate": 0.00019025191675794086, |
| "loss": 0.2661, |
| "step": 1770 |
| }, |
| { |
| "epoch": 1.144694533762058, |
| "grad_norm": 0.16947688162326813, |
| "learning_rate": 0.00018959474260679077, |
| "loss": 0.2635, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.1511254019292605, |
| "grad_norm": 0.16996344923973083, |
| "learning_rate": 0.00018893756845564074, |
| "loss": 0.2612, |
| "step": 1790 |
| }, |
| { |
| "epoch": 1.157556270096463, |
| "grad_norm": 0.16218321025371552, |
| "learning_rate": 0.00018828039430449068, |
| "loss": 0.2614, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.157556270096463, |
| "eval_loss": 0.2809600234031677, |
| "eval_runtime": 829.6019, |
| "eval_samples_per_second": 2.411, |
| "eval_steps_per_second": 2.411, |
| "step": 1800 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 4665, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.64707486237098e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
