| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023342261748452116, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023342261748452117, | |
| "grad_norm": 0.2070077508687973, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00046684523496904234, | |
| "grad_norm": 0.2195936143398285, | |
| "learning_rate": 0.0001959183673469388, | |
| "loss": 1.1291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007002678524535634, | |
| "grad_norm": 0.1822710633277893, | |
| "learning_rate": 0.00019183673469387756, | |
| "loss": 0.6041, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009336904699380847, | |
| "grad_norm": 0.10866066068410873, | |
| "learning_rate": 0.00018775510204081634, | |
| "loss": 0.5399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011671130874226058, | |
| "grad_norm": 0.06832244247198105, | |
| "learning_rate": 0.00018367346938775512, | |
| "loss": 0.4337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0014005357049071269, | |
| "grad_norm": 0.13112975656986237, | |
| "learning_rate": 0.0001795918367346939, | |
| "loss": 0.4785, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0016339583223916481, | |
| "grad_norm": 0.05374117195606232, | |
| "learning_rate": 0.00017551020408163265, | |
| "loss": 0.4458, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0018673809398761694, | |
| "grad_norm": 0.049559202045202255, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 0.4517, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0021008035573606906, | |
| "grad_norm": 0.10584782809019089, | |
| "learning_rate": 0.00016734693877551023, | |
| "loss": 0.4592, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0023342261748452117, | |
| "grad_norm": 0.062141530215740204, | |
| "learning_rate": 0.00016326530612244898, | |
| "loss": 0.4625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0025676487923297327, | |
| "grad_norm": 0.14701640605926514, | |
| "learning_rate": 0.00015918367346938776, | |
| "loss": 0.4818, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0028010714098142537, | |
| "grad_norm": 0.048784978687763214, | |
| "learning_rate": 0.00015510204081632654, | |
| "loss": 0.4687, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003034494027298775, | |
| "grad_norm": 0.05522393435239792, | |
| "learning_rate": 0.0001510204081632653, | |
| "loss": 0.4576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0032679166447832962, | |
| "grad_norm": 0.05478575825691223, | |
| "learning_rate": 0.0001469387755102041, | |
| "loss": 0.4666, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0035013392622678173, | |
| "grad_norm": 0.09066344797611237, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 0.4168, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0037347618797523388, | |
| "grad_norm": 0.054524753242731094, | |
| "learning_rate": 0.00013877551020408165, | |
| "loss": 0.4813, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.00396818449723686, | |
| "grad_norm": 0.12929686903953552, | |
| "learning_rate": 0.0001346938775510204, | |
| "loss": 0.4981, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.004201607114721381, | |
| "grad_norm": 0.05895541235804558, | |
| "learning_rate": 0.00013061224489795917, | |
| "loss": 0.4078, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.004435029732205902, | |
| "grad_norm": 0.05701744183897972, | |
| "learning_rate": 0.00012653061224489798, | |
| "loss": 0.4323, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.004668452349690423, | |
| "grad_norm": 0.10815092921257019, | |
| "learning_rate": 0.00012244897959183676, | |
| "loss": 0.5232, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004901874967174945, | |
| "grad_norm": 0.1338973492383957, | |
| "learning_rate": 0.00011836734693877552, | |
| "loss": 0.5053, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.005135297584659465, | |
| "grad_norm": 0.04165051504969597, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 0.4149, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.005368720202143987, | |
| "grad_norm": 0.05300717428326607, | |
| "learning_rate": 0.00011020408163265306, | |
| "loss": 0.444, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.0056021428196285075, | |
| "grad_norm": 0.1370624154806137, | |
| "learning_rate": 0.00010612244897959185, | |
| "loss": 0.4525, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.005835565437113029, | |
| "grad_norm": 0.049909207969903946, | |
| "learning_rate": 0.00010204081632653062, | |
| "loss": 0.4497, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.00606898805459755, | |
| "grad_norm": 0.110743448138237, | |
| "learning_rate": 9.79591836734694e-05, | |
| "loss": 0.4837, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.006302410672082071, | |
| "grad_norm": 0.09541227668523788, | |
| "learning_rate": 9.387755102040817e-05, | |
| "loss": 0.49, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.0065358332895665925, | |
| "grad_norm": 0.05263066291809082, | |
| "learning_rate": 8.979591836734695e-05, | |
| "loss": 0.4437, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.006769255907051114, | |
| "grad_norm": 0.09211356937885284, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 0.4479, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.007002678524535635, | |
| "grad_norm": 0.05164729803800583, | |
| "learning_rate": 8.163265306122449e-05, | |
| "loss": 0.4329, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.007236101142020156, | |
| "grad_norm": 0.08837030827999115, | |
| "learning_rate": 7.755102040816327e-05, | |
| "loss": 0.4533, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.0074695237595046775, | |
| "grad_norm": 0.0369272343814373, | |
| "learning_rate": 7.346938775510205e-05, | |
| "loss": 0.3667, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.007702946376989198, | |
| "grad_norm": 0.059746578335762024, | |
| "learning_rate": 6.938775510204082e-05, | |
| "loss": 0.424, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.00793636899447372, | |
| "grad_norm": 0.04736114665865898, | |
| "learning_rate": 6.530612244897959e-05, | |
| "loss": 0.4538, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.00816979161195824, | |
| "grad_norm": 0.04814208671450615, | |
| "learning_rate": 6.122448979591838e-05, | |
| "loss": 0.4894, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.008403214229442763, | |
| "grad_norm": 0.04663668945431709, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 0.5158, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.008636636846927283, | |
| "grad_norm": 0.08329813182353973, | |
| "learning_rate": 5.3061224489795926e-05, | |
| "loss": 0.5901, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.008870059464411804, | |
| "grad_norm": 0.0947406217455864, | |
| "learning_rate": 4.89795918367347e-05, | |
| "loss": 0.4438, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.009103482081896326, | |
| "grad_norm": 0.048670731484889984, | |
| "learning_rate": 4.4897959183673474e-05, | |
| "loss": 0.4304, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.009336904699380847, | |
| "grad_norm": 0.12740883231163025, | |
| "learning_rate": 4.0816326530612245e-05, | |
| "loss": 0.5186, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.009570327316865367, | |
| "grad_norm": 0.13359272480010986, | |
| "learning_rate": 3.673469387755102e-05, | |
| "loss": 0.5146, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.00980374993434989, | |
| "grad_norm": 0.07435787469148636, | |
| "learning_rate": 3.265306122448979e-05, | |
| "loss": 0.4666, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.01003717255183441, | |
| "grad_norm": 0.05466726794838905, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.3812, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.01027059516931893, | |
| "grad_norm": 0.05390426889061928, | |
| "learning_rate": 2.448979591836735e-05, | |
| "loss": 0.4026, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.010504017786803453, | |
| "grad_norm": 0.055242184549570084, | |
| "learning_rate": 2.0408163265306123e-05, | |
| "loss": 0.437, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.010737440404287974, | |
| "grad_norm": 0.03994165360927582, | |
| "learning_rate": 1.6326530612244897e-05, | |
| "loss": 0.4343, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.010970863021772494, | |
| "grad_norm": 0.04847300797700882, | |
| "learning_rate": 1.2244897959183674e-05, | |
| "loss": 0.4618, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.011204285639257015, | |
| "grad_norm": 0.08686497807502747, | |
| "learning_rate": 8.163265306122448e-06, | |
| "loss": 0.4264, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.011437708256741537, | |
| "grad_norm": 0.09176526963710785, | |
| "learning_rate": 4.081632653061224e-06, | |
| "loss": 0.5168, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.011671130874226058, | |
| "grad_norm": 0.10465481132268906, | |
| "learning_rate": 0.0, | |
| "loss": 0.4519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.011904553491710579, | |
| "grad_norm": 0.051657382398843765, | |
| "learning_rate": 9.8989898989899e-05, | |
| "loss": 0.4728, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.0121379761091951, | |
| "grad_norm": 0.062193650752305984, | |
| "learning_rate": 9.696969696969698e-05, | |
| "loss": 0.4483, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.012371398726679621, | |
| "grad_norm": 0.06362653523683548, | |
| "learning_rate": 9.494949494949495e-05, | |
| "loss": 0.4215, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.012604821344164142, | |
| "grad_norm": 0.06238653138279915, | |
| "learning_rate": 9.292929292929293e-05, | |
| "loss": 0.4224, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.012838243961648664, | |
| "grad_norm": 0.0477604866027832, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.448, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.013071666579133185, | |
| "grad_norm": 0.09850312024354935, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.4424, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.013305089196617706, | |
| "grad_norm": 0.06217048689723015, | |
| "learning_rate": 8.686868686868688e-05, | |
| "loss": 0.3644, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.013538511814102228, | |
| "grad_norm": 0.043189432471990585, | |
| "learning_rate": 8.484848484848486e-05, | |
| "loss": 0.4564, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.013771934431586749, | |
| "grad_norm": 0.10206077247858047, | |
| "learning_rate": 8.282828282828283e-05, | |
| "loss": 0.4176, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.01400535704907127, | |
| "grad_norm": 0.05712655559182167, | |
| "learning_rate": 8.080808080808081e-05, | |
| "loss": 0.3896, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.014238779666555791, | |
| "grad_norm": 0.04486239328980446, | |
| "learning_rate": 7.878787878787879e-05, | |
| "loss": 0.3761, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.014472202284040312, | |
| "grad_norm": 0.043401289731264114, | |
| "learning_rate": 7.676767676767676e-05, | |
| "loss": 0.4471, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.014705624901524833, | |
| "grad_norm": 0.4940922260284424, | |
| "learning_rate": 7.474747474747475e-05, | |
| "loss": 0.4569, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.014939047519009355, | |
| "grad_norm": 0.10270397365093231, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.4805, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.015172470136493876, | |
| "grad_norm": 0.13152533769607544, | |
| "learning_rate": 7.07070707070707e-05, | |
| "loss": 0.5194, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.015405892753978396, | |
| "grad_norm": 0.07382863759994507, | |
| "learning_rate": 6.86868686868687e-05, | |
| "loss": 0.4161, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.015639315371462917, | |
| "grad_norm": 0.08843934535980225, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.5265, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01587273798894744, | |
| "grad_norm": 0.053686585277318954, | |
| "learning_rate": 6.464646464646466e-05, | |
| "loss": 0.4667, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.01610616060643196, | |
| "grad_norm": 0.05910225212574005, | |
| "learning_rate": 6.262626262626264e-05, | |
| "loss": 0.4254, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.01633958322391648, | |
| "grad_norm": 0.039652127772569656, | |
| "learning_rate": 6.060606060606061e-05, | |
| "loss": 0.4511, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.016573005841401003, | |
| "grad_norm": 0.0999956876039505, | |
| "learning_rate": 5.858585858585859e-05, | |
| "loss": 0.4396, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.016806428458885525, | |
| "grad_norm": 0.03926937282085419, | |
| "learning_rate": 5.6565656565656563e-05, | |
| "loss": 0.4178, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.017039851076370044, | |
| "grad_norm": 0.09462181478738785, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.4092, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.017273273693854566, | |
| "grad_norm": 0.05022445321083069, | |
| "learning_rate": 5.2525252525252536e-05, | |
| "loss": 0.422, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.01750669631133909, | |
| "grad_norm": 0.10167255997657776, | |
| "learning_rate": 5.050505050505051e-05, | |
| "loss": 0.4028, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.017740118928823607, | |
| "grad_norm": 0.0910029336810112, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.4341, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.01797354154630813, | |
| "grad_norm": 0.047616615891456604, | |
| "learning_rate": 4.6464646464646464e-05, | |
| "loss": 0.411, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.018206964163792652, | |
| "grad_norm": 0.08828525990247726, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.4616, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.01844038678127717, | |
| "grad_norm": 0.044807884842157364, | |
| "learning_rate": 4.242424242424243e-05, | |
| "loss": 0.4865, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.018673809398761693, | |
| "grad_norm": 0.08502307534217834, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.4624, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.018907232016246216, | |
| "grad_norm": 0.1129627451300621, | |
| "learning_rate": 3.838383838383838e-05, | |
| "loss": 0.4338, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.019140654633730735, | |
| "grad_norm": 0.10634730011224747, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.5142, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.019374077251215257, | |
| "grad_norm": 0.04792294651269913, | |
| "learning_rate": 3.434343434343435e-05, | |
| "loss": 0.4286, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.01960749986869978, | |
| "grad_norm": 0.046725083142519, | |
| "learning_rate": 3.232323232323233e-05, | |
| "loss": 0.4116, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.019840922486184298, | |
| "grad_norm": 0.052620138972997665, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.4141, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.02007434510366882, | |
| "grad_norm": 0.10660973191261292, | |
| "learning_rate": 2.8282828282828282e-05, | |
| "loss": 0.4347, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.020307767721153343, | |
| "grad_norm": 0.0386226549744606, | |
| "learning_rate": 2.6262626262626268e-05, | |
| "loss": 0.4461, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.02054119033863786, | |
| "grad_norm": 0.07292847335338593, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.4355, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.020774612956122384, | |
| "grad_norm": 0.06434612721204758, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.5035, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.021008035573606906, | |
| "grad_norm": 0.10716721415519714, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.3866, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.021241458191091425, | |
| "grad_norm": 0.04890590161085129, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.3767, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.021474880808575948, | |
| "grad_norm": 0.06173992156982422, | |
| "learning_rate": 1.6161616161616165e-05, | |
| "loss": 0.4063, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.021708303426060466, | |
| "grad_norm": 0.053141020238399506, | |
| "learning_rate": 1.4141414141414141e-05, | |
| "loss": 0.4751, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.02194172604354499, | |
| "grad_norm": 0.05243794620037079, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.4625, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.02217514866102951, | |
| "grad_norm": 0.061262525618076324, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.4492, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.02240857127851403, | |
| "grad_norm": 0.10454926639795303, | |
| "learning_rate": 8.080808080808082e-06, | |
| "loss": 0.4522, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.022641993895998552, | |
| "grad_norm": 0.05348167195916176, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 0.434, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.022875416513483075, | |
| "grad_norm": 0.1315009742975235, | |
| "learning_rate": 4.040404040404041e-06, | |
| "loss": 0.5003, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.023108839130967593, | |
| "grad_norm": 0.0520632266998291, | |
| "learning_rate": 2.0202020202020206e-06, | |
| "loss": 0.3953, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.023342261748452116, | |
| "grad_norm": 0.08680278062820435, | |
| "learning_rate": 0.0, | |
| "loss": 0.432, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.170835390089626e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |