| { | |
| "best_metric": 1.877977728843689, | |
| "best_model_checkpoint": "./output/checkpoint-450", | |
| "epoch": 0.14511447920025797, | |
| "eval_steps": 150, | |
| "global_step": 1350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001074922068150059, | |
| "grad_norm": 43.13871765136719, | |
| "learning_rate": 4.125e-06, | |
| "loss": 2.2922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002149844136300118, | |
| "grad_norm": 26.323883056640625, | |
| "learning_rate": 8.25e-06, | |
| "loss": 2.1328, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0032247662044501773, | |
| "grad_norm": 17.629505157470703, | |
| "learning_rate": 1.2375e-05, | |
| "loss": 2.036, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004299688272600236, | |
| "grad_norm": 10.648378372192383, | |
| "learning_rate": 1.65e-05, | |
| "loss": 1.851, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005374610340750295, | |
| "grad_norm": 17.73092269897461, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 1.8746, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0064495324089003546, | |
| "grad_norm": 6.716779708862305, | |
| "learning_rate": 2.475e-05, | |
| "loss": 1.8512, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.007524454477050414, | |
| "grad_norm": 15.877828598022461, | |
| "learning_rate": 2.8874999999999997e-05, | |
| "loss": 1.9416, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008599376545200472, | |
| "grad_norm": 14.675684928894043, | |
| "learning_rate": 3.3e-05, | |
| "loss": 1.8581, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009674298613350531, | |
| "grad_norm": 11.489137649536133, | |
| "learning_rate": 3.7125e-05, | |
| "loss": 1.9017, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01074922068150059, | |
| "grad_norm": 7.483497619628906, | |
| "learning_rate": 4.125e-05, | |
| "loss": 1.9335, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01182414274965065, | |
| "grad_norm": 9.6410551071167, | |
| "learning_rate": 4.12495760935163e-05, | |
| "loss": 1.7841, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.012899064817800709, | |
| "grad_norm": 7.8748979568481445, | |
| "learning_rate": 4.1248304391490334e-05, | |
| "loss": 1.8529, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.013973986885950768, | |
| "grad_norm": 9.455327987670898, | |
| "learning_rate": 4.1246184946196796e-05, | |
| "loss": 1.9366, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.015048908954100828, | |
| "grad_norm": 8.64035701751709, | |
| "learning_rate": 4.124321784475777e-05, | |
| "loss": 1.8501, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.016123831022250887, | |
| "grad_norm": 13.220332145690918, | |
| "learning_rate": 4.123940320913919e-05, | |
| "loss": 1.9095, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.016123831022250887, | |
| "eval_loss": 1.8831839561462402, | |
| "eval_runtime": 61.5136, | |
| "eval_samples_per_second": 8.128, | |
| "eval_steps_per_second": 8.128, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.017198753090400944, | |
| "grad_norm": 8.182404518127441, | |
| "learning_rate": 4.123474119614577e-05, | |
| "loss": 1.8163, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.018273675158551005, | |
| "grad_norm": 12.389548301696777, | |
| "learning_rate": 4.1229231997414614e-05, | |
| "loss": 1.8781, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.019348597226701063, | |
| "grad_norm": 8.600774765014648, | |
| "learning_rate": 4.1222875839407306e-05, | |
| "loss": 1.8206, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.020423519294851124, | |
| "grad_norm": 7.161348819732666, | |
| "learning_rate": 4.121567298340059e-05, | |
| "loss": 1.8117, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02149844136300118, | |
| "grad_norm": 7.655135631561279, | |
| "learning_rate": 4.120762372547569e-05, | |
| "loss": 1.794, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 10.144853591918945, | |
| "learning_rate": 4.119872839650605e-05, | |
| "loss": 1.8959, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0236482854993013, | |
| "grad_norm": 8.557960510253906, | |
| "learning_rate": 4.118898736214381e-05, | |
| "loss": 1.8676, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.02472320756745136, | |
| "grad_norm": 11.726237297058105, | |
| "learning_rate": 4.117840102280475e-05, | |
| "loss": 1.7744, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.025798129635601418, | |
| "grad_norm": 8.739320755004883, | |
| "learning_rate": 4.116696981365181e-05, | |
| "loss": 1.8178, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.02687305170375148, | |
| "grad_norm": 6.433278560638428, | |
| "learning_rate": 4.115469420457721e-05, | |
| "loss": 1.7578, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.027947973771901537, | |
| "grad_norm": 6.021564960479736, | |
| "learning_rate": 4.1141574700183186e-05, | |
| "loss": 1.8376, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.029022895840051598, | |
| "grad_norm": 8.607327461242676, | |
| "learning_rate": 4.1127611839761155e-05, | |
| "loss": 1.7681, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.030097817908201655, | |
| "grad_norm": 9.417404174804688, | |
| "learning_rate": 4.111280619726964e-05, | |
| "loss": 1.8459, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.031172739976351716, | |
| "grad_norm": 11.03150749206543, | |
| "learning_rate": 4.109715838131059e-05, | |
| "loss": 1.8467, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.032247662044501774, | |
| "grad_norm": 7.549683570861816, | |
| "learning_rate": 4.108066903510445e-05, | |
| "loss": 1.8979, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.032247662044501774, | |
| "eval_loss": 1.8808292150497437, | |
| "eval_runtime": 60.731, | |
| "eval_samples_per_second": 8.233, | |
| "eval_steps_per_second": 8.233, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.033322584112651835, | |
| "grad_norm": 7.343403339385986, | |
| "learning_rate": 4.106333883646366e-05, | |
| "loss": 1.8544, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.03439750618080189, | |
| "grad_norm": 6.203611850738525, | |
| "learning_rate": 4.104516849776479e-05, | |
| "loss": 1.8245, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.03547242824895195, | |
| "grad_norm": 8.674558639526367, | |
| "learning_rate": 4.1026158765919306e-05, | |
| "loss": 1.8058, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.03654735031710201, | |
| "grad_norm": 9.196893692016602, | |
| "learning_rate": 4.100631042234283e-05, | |
| "loss": 1.8813, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.03762227238525207, | |
| "grad_norm": 10.656414985656738, | |
| "learning_rate": 4.098562428292304e-05, | |
| "loss": 1.7876, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.038697194453402126, | |
| "grad_norm": 6.581936836242676, | |
| "learning_rate": 4.096410119798607e-05, | |
| "loss": 1.8134, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.03977211652155219, | |
| "grad_norm": 9.650823593139648, | |
| "learning_rate": 4.094174205226167e-05, | |
| "loss": 1.7727, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.04084703858970225, | |
| "grad_norm": 10.17803955078125, | |
| "learning_rate": 4.0918547764846736e-05, | |
| "loss": 1.7945, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.04192196065785231, | |
| "grad_norm": 8.77602481842041, | |
| "learning_rate": 4.089451928916758e-05, | |
| "loss": 1.9062, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.04299688272600236, | |
| "grad_norm": 6.488632678985596, | |
| "learning_rate": 4.0869657612940723e-05, | |
| "loss": 1.774, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.044071804794152424, | |
| "grad_norm": 10.849347114562988, | |
| "learning_rate": 4.08439637581323e-05, | |
| "loss": 1.8497, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 6.79919958114624, | |
| "learning_rate": 4.081743878091604e-05, | |
| "loss": 1.9205, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.046221648930452545, | |
| "grad_norm": 10.169675827026367, | |
| "learning_rate": 4.079008377162988e-05, | |
| "loss": 1.8459, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.0472965709986026, | |
| "grad_norm": 6.641557216644287, | |
| "learning_rate": 4.0761899854731085e-05, | |
| "loss": 1.867, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.04837149306675266, | |
| "grad_norm": 10.017315864562988, | |
| "learning_rate": 4.073288818875011e-05, | |
| "loss": 1.8095, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.04837149306675266, | |
| "eval_loss": 1.877977728843689, | |
| "eval_runtime": 60.8543, | |
| "eval_samples_per_second": 8.216, | |
| "eval_steps_per_second": 8.216, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.04944641513490272, | |
| "grad_norm": 7.070505619049072, | |
| "learning_rate": 4.070304996624291e-05, | |
| "loss": 1.8261, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.050521337203052775, | |
| "grad_norm": 7.832033157348633, | |
| "learning_rate": 4.067238641374194e-05, | |
| "loss": 1.8129, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.051596259271202836, | |
| "grad_norm": 8.640854835510254, | |
| "learning_rate": 4.0640898791705745e-05, | |
| "loss": 1.8887, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.0526711813393529, | |
| "grad_norm": 8.050338745117188, | |
| "learning_rate": 4.060858839446713e-05, | |
| "loss": 1.8551, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.05374610340750296, | |
| "grad_norm": 5.903382778167725, | |
| "learning_rate": 4.057545655017998e-05, | |
| "loss": 1.7708, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05482102547565301, | |
| "grad_norm": 6.558720111846924, | |
| "learning_rate": 4.054150462076465e-05, | |
| "loss": 1.8277, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.05589594754380307, | |
| "grad_norm": 9.94021224975586, | |
| "learning_rate": 4.0506734001851976e-05, | |
| "loss": 1.8834, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.056970869611953134, | |
| "grad_norm": 11.147041320800781, | |
| "learning_rate": 4.0471146122725904e-05, | |
| "loss": 1.8697, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.058045791680103195, | |
| "grad_norm": 7.040550708770752, | |
| "learning_rate": 4.043474244626477e-05, | |
| "loss": 1.8605, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.05912071374825325, | |
| "grad_norm": 8.166383743286133, | |
| "learning_rate": 4.0397524468881125e-05, | |
| "loss": 1.8772, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.06019563581640331, | |
| "grad_norm": 6.262266159057617, | |
| "learning_rate": 4.0359493720460244e-05, | |
| "loss": 1.8334, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.06127055788455337, | |
| "grad_norm": 6.04037618637085, | |
| "learning_rate": 4.032065176429724e-05, | |
| "loss": 1.8355, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.06234547995270343, | |
| "grad_norm": 6.709385871887207, | |
| "learning_rate": 4.0281000197032795e-05, | |
| "loss": 1.8567, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.06342040202085349, | |
| "grad_norm": 6.928658962249756, | |
| "learning_rate": 4.0240540648587546e-05, | |
| "loss": 1.8503, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.06449532408900355, | |
| "grad_norm": 5.788703918457031, | |
| "learning_rate": 4.019927478209504e-05, | |
| "loss": 1.8522, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06449532408900355, | |
| "eval_loss": 1.8825602531433105, | |
| "eval_runtime": 60.165, | |
| "eval_samples_per_second": 8.31, | |
| "eval_steps_per_second": 8.31, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06557024615715361, | |
| "grad_norm": 9.176572799682617, | |
| "learning_rate": 4.015720429383344e-05, | |
| "loss": 1.8688, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.06664516822530367, | |
| "grad_norm": 7.160205841064453, | |
| "learning_rate": 4.0114330913155726e-05, | |
| "loss": 1.8031, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "grad_norm": 9.988216400146484, | |
| "learning_rate": 4.007065640241867e-05, | |
| "loss": 1.8262, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.06879501236160378, | |
| "grad_norm": 9.315797805786133, | |
| "learning_rate": 4.002618255691033e-05, | |
| "loss": 1.8542, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.06986993442975384, | |
| "grad_norm": 7.385815143585205, | |
| "learning_rate": 3.9980911204776306e-05, | |
| "loss": 1.8328, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.0709448564979039, | |
| "grad_norm": 7.70832633972168, | |
| "learning_rate": 3.993484420694458e-05, | |
| "loss": 1.9542, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.07201977856605396, | |
| "grad_norm": 10.131119728088379, | |
| "learning_rate": 3.988798345704899e-05, | |
| "loss": 1.8389, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.07309470063420402, | |
| "grad_norm": 6.0609354972839355, | |
| "learning_rate": 3.984033088135143e-05, | |
| "loss": 1.8653, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.07416962270235408, | |
| "grad_norm": 9.173294067382812, | |
| "learning_rate": 3.979188843866263e-05, | |
| "loss": 1.8558, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.07524454477050414, | |
| "grad_norm": 5.944100856781006, | |
| "learning_rate": 3.97426581202617e-05, | |
| "loss": 1.922, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0763194668386542, | |
| "grad_norm": 7.453153133392334, | |
| "learning_rate": 3.969264194981418e-05, | |
| "loss": 1.8524, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.07739438890680425, | |
| "grad_norm": 6.75320291519165, | |
| "learning_rate": 3.9641841983288953e-05, | |
| "loss": 1.8699, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.07846931097495431, | |
| "grad_norm": 6.539112567901611, | |
| "learning_rate": 3.959026030887367e-05, | |
| "loss": 1.7784, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.07954423304310437, | |
| "grad_norm": 7.794706344604492, | |
| "learning_rate": 3.953789904688893e-05, | |
| "loss": 1.8222, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.08061915511125443, | |
| "grad_norm": 7.376310348510742, | |
| "learning_rate": 3.948476034970113e-05, | |
| "loss": 1.7985, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.08061915511125443, | |
| "eval_loss": 1.8882893323898315, | |
| "eval_runtime": 60.264, | |
| "eval_samples_per_second": 8.297, | |
| "eval_steps_per_second": 8.297, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.0816940771794045, | |
| "grad_norm": 8.657331466674805, | |
| "learning_rate": 3.943084640163398e-05, | |
| "loss": 1.7983, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.08276899924755456, | |
| "grad_norm": 5.748507976531982, | |
| "learning_rate": 3.937615941887873e-05, | |
| "loss": 1.884, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.08384392131570462, | |
| "grad_norm": 6.509608745574951, | |
| "learning_rate": 3.932070164940304e-05, | |
| "loss": 1.891, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.08491884338385466, | |
| "grad_norm": 6.634593486785889, | |
| "learning_rate": 3.926447537285859e-05, | |
| "loss": 1.776, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.08599376545200473, | |
| "grad_norm": 9.289311408996582, | |
| "learning_rate": 3.920748290048739e-05, | |
| "loss": 1.7806, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.08706868752015479, | |
| "grad_norm": 7.693164348602295, | |
| "learning_rate": 3.914972657502677e-05, | |
| "loss": 1.8428, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.08814360958830485, | |
| "grad_norm": 5.920309066772461, | |
| "learning_rate": 3.9091208770613036e-05, | |
| "loss": 1.8048, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.08921853165645491, | |
| "grad_norm": 7.512606143951416, | |
| "learning_rate": 3.9031931892683937e-05, | |
| "loss": 1.848, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 8.341816902160645, | |
| "learning_rate": 3.897189837787975e-05, | |
| "loss": 1.7995, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.09136837579275503, | |
| "grad_norm": 7.76444149017334, | |
| "learning_rate": 3.891111069394313e-05, | |
| "loss": 1.7587, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.09244329786090509, | |
| "grad_norm": 8.347227096557617, | |
| "learning_rate": 3.884957133961768e-05, | |
| "loss": 1.8215, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.09351821992905514, | |
| "grad_norm": 7.596982955932617, | |
| "learning_rate": 3.878728284454522e-05, | |
| "loss": 1.8831, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.0945931419972052, | |
| "grad_norm": 7.217879295349121, | |
| "learning_rate": 3.872424776916183e-05, | |
| "loss": 1.9871, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.09566806406535526, | |
| "grad_norm": 6.474759101867676, | |
| "learning_rate": 3.866046870459253e-05, | |
| "loss": 1.8137, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.09674298613350532, | |
| "grad_norm": 7.693883419036865, | |
| "learning_rate": 3.8595948272544905e-05, | |
| "loss": 1.884, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.09674298613350532, | |
| "eval_loss": 1.8837863206863403, | |
| "eval_runtime": 61.2639, | |
| "eval_samples_per_second": 8.161, | |
| "eval_steps_per_second": 8.161, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.09781790820165538, | |
| "grad_norm": 7.503582954406738, | |
| "learning_rate": 3.8530689125201184e-05, | |
| "loss": 1.8213, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.09889283026980544, | |
| "grad_norm": 7.769185543060303, | |
| "learning_rate": 3.8464693945109305e-05, | |
| "loss": 1.8505, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.0999677523379555, | |
| "grad_norm": 7.26152229309082, | |
| "learning_rate": 3.839796544507265e-05, | |
| "loss": 1.8225, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.10104267440610555, | |
| "grad_norm": 7.977392673492432, | |
| "learning_rate": 3.833050636803849e-05, | |
| "loss": 1.8483, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.10211759647425561, | |
| "grad_norm": 8.005775451660156, | |
| "learning_rate": 3.826231948698527e-05, | |
| "loss": 1.9364, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.10319251854240567, | |
| "grad_norm": 6.598343849182129, | |
| "learning_rate": 3.819340760480859e-05, | |
| "loss": 1.8967, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.10426744061055573, | |
| "grad_norm": 8.264419555664062, | |
| "learning_rate": 3.812377355420602e-05, | |
| "loss": 1.791, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.1053423626787058, | |
| "grad_norm": 7.987963676452637, | |
| "learning_rate": 3.805342019756065e-05, | |
| "loss": 1.8654, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.10641728474685586, | |
| "grad_norm": 8.105964660644531, | |
| "learning_rate": 3.7982350426823406e-05, | |
| "loss": 1.854, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.10749220681500592, | |
| "grad_norm": 8.088004112243652, | |
| "learning_rate": 3.791056716339421e-05, | |
| "loss": 1.8123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10856712888315598, | |
| "grad_norm": 9.775269508361816, | |
| "learning_rate": 3.783807335800187e-05, | |
| "loss": 1.8431, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.10964205095130602, | |
| "grad_norm": 6.646794319152832, | |
| "learning_rate": 3.776487199058277e-05, | |
| "loss": 1.8865, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.11071697301945609, | |
| "grad_norm": 7.902348041534424, | |
| "learning_rate": 3.769096607015843e-05, | |
| "loss": 1.8599, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.11179189508760615, | |
| "grad_norm": 6.932212829589844, | |
| "learning_rate": 3.761635863471175e-05, | |
| "loss": 1.8696, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "grad_norm": 8.541101455688477, | |
| "learning_rate": 3.754105275106222e-05, | |
| "loss": 1.7824, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "eval_loss": 1.8909525871276855, | |
| "eval_runtime": 60.951, | |
| "eval_samples_per_second": 8.203, | |
| "eval_steps_per_second": 8.203, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.11394173922390627, | |
| "grad_norm": 6.613965034484863, | |
| "learning_rate": 3.746505151473972e-05, | |
| "loss": 1.8719, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.11501666129205633, | |
| "grad_norm": 7.055614948272705, | |
| "learning_rate": 3.738835804985743e-05, | |
| "loss": 1.8533, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.11609158336020639, | |
| "grad_norm": 8.038810729980469, | |
| "learning_rate": 3.731097550898329e-05, | |
| "loss": 1.8067, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.11716650542835644, | |
| "grad_norm": 6.726877689361572, | |
| "learning_rate": 3.723290707301047e-05, | |
| "loss": 1.8871, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.1182414274965065, | |
| "grad_norm": 7.802327632904053, | |
| "learning_rate": 3.7154155951026605e-05, | |
| "loss": 2.0685, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.11931634956465656, | |
| "grad_norm": 8.144506454467773, | |
| "learning_rate": 3.707472538018187e-05, | |
| "loss": 1.9074, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.12039127163280662, | |
| "grad_norm": 11.114158630371094, | |
| "learning_rate": 3.6994618625555925e-05, | |
| "loss": 1.8036, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.12146619370095668, | |
| "grad_norm": 8.913481712341309, | |
| "learning_rate": 3.691383898002368e-05, | |
| "loss": 1.8411, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.12254111576910674, | |
| "grad_norm": 7.231012344360352, | |
| "learning_rate": 3.683238976412e-05, | |
| "loss": 1.838, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.1236160378372568, | |
| "grad_norm": 7.460425853729248, | |
| "learning_rate": 3.675027432590312e-05, | |
| "loss": 1.907, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.12469095990540686, | |
| "grad_norm": 6.360142230987549, | |
| "learning_rate": 3.666749604081707e-05, | |
| "loss": 1.8568, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.12576588197355693, | |
| "grad_norm": 8.225682258605957, | |
| "learning_rate": 3.6584058311552954e-05, | |
| "loss": 1.8473, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.12684080404170697, | |
| "grad_norm": 8.119696617126465, | |
| "learning_rate": 3.6499964567909e-05, | |
| "loss": 1.7953, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.12791572610985705, | |
| "grad_norm": 7.61316442489624, | |
| "learning_rate": 3.641521826664964e-05, | |
| "loss": 1.7599, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.1289906481780071, | |
| "grad_norm": 7.965550422668457, | |
| "learning_rate": 3.63298228913634e-05, | |
| "loss": 1.8461, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1289906481780071, | |
| "eval_loss": 1.8840419054031372, | |
| "eval_runtime": 62.5093, | |
| "eval_samples_per_second": 7.999, | |
| "eval_steps_per_second": 7.999, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.13006557024615714, | |
| "grad_norm": 5.871341228485107, | |
| "learning_rate": 3.624378195231967e-05, | |
| "loss": 1.8397, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.13114049231430722, | |
| "grad_norm": 18.254127502441406, | |
| "learning_rate": 3.615709898632448e-05, | |
| "loss": 1.8295, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.13221541438245726, | |
| "grad_norm": 8.392979621887207, | |
| "learning_rate": 3.606977755657502e-05, | |
| "loss": 1.8058, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.13329033645060734, | |
| "grad_norm": 10.364768981933594, | |
| "learning_rate": 3.5981821252513274e-05, | |
| "loss": 1.8656, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.13436525851875739, | |
| "grad_norm": 6.204119682312012, | |
| "learning_rate": 3.5893233689678384e-05, | |
| "loss": 1.8201, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.13544018058690746, | |
| "grad_norm": 8.470161437988281, | |
| "learning_rate": 3.5804018509558095e-05, | |
| "loss": 1.8629, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.1365151026550575, | |
| "grad_norm": 7.885449409484863, | |
| "learning_rate": 3.571417937943903e-05, | |
| "loss": 1.9337, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.13759002472320755, | |
| "grad_norm": 6.3673996925354, | |
| "learning_rate": 3.562371999225594e-05, | |
| "loss": 1.8661, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.13866494679135763, | |
| "grad_norm": 9.29290771484375, | |
| "learning_rate": 3.553264406643995e-05, | |
| "loss": 1.7597, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.13973986885950768, | |
| "grad_norm": 6.828396320343018, | |
| "learning_rate": 3.544095534576563e-05, | |
| "loss": 1.8641, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.14081479092765775, | |
| "grad_norm": 9.610004425048828, | |
| "learning_rate": 3.534865759919718e-05, | |
| "loss": 1.8846, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.1418897129958078, | |
| "grad_norm": 7.615134239196777, | |
| "learning_rate": 3.525575462073344e-05, | |
| "loss": 1.885, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.14296463506395787, | |
| "grad_norm": 7.668911933898926, | |
| "learning_rate": 3.516225022925199e-05, | |
| "loss": 1.79, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.14403955713210792, | |
| "grad_norm": 7.5038042068481445, | |
| "learning_rate": 3.5068148268352135e-05, | |
| "loss": 1.8394, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.14511447920025797, | |
| "grad_norm": 7.994359970092773, | |
| "learning_rate": 3.497345260619691e-05, | |
| "loss": 1.8393, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.14511447920025797, | |
| "eval_loss": 1.8796833753585815, | |
| "eval_runtime": 57.9394, | |
| "eval_samples_per_second": 8.63, | |
| "eval_steps_per_second": 8.63, | |
| "step": 1350 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.751283405814497e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |