| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 91.78527607361963, | |
| "eval_steps": 2, | |
| "global_step": 92, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7852760736196319, | |
| "grad_norm": 2.828015891236112, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.7344894409179688, | |
| "memory(GiB)": 33.35, | |
| "step": 1, | |
| "token_acc": 0.8210270474011879, | |
| "train_speed(iter/s)": 0.01508 | |
| }, | |
| { | |
| "epoch": 1.7852760736196318, | |
| "grad_norm": 5.560922634626607, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.4670829772949219, | |
| "memory(GiB)": 39.33, | |
| "step": 2, | |
| "token_acc": 0.8254568857425018, | |
| "train_speed(iter/s)": 0.015066 | |
| }, | |
| { | |
| "epoch": 2.785276073619632, | |
| "grad_norm": 5.459222412898219, | |
| "learning_rate": 1.5e-06, | |
| "loss": 1.452088713645935, | |
| "memory(GiB)": 39.33, | |
| "step": 3, | |
| "token_acc": 0.8195757791207489, | |
| "train_speed(iter/s)": 0.014624 | |
| }, | |
| { | |
| "epoch": 3.785276073619632, | |
| "grad_norm": 5.463168612488766, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.4775556325912476, | |
| "memory(GiB)": 39.33, | |
| "step": 4, | |
| "token_acc": 0.823338222352596, | |
| "train_speed(iter/s)": 0.014761 | |
| }, | |
| { | |
| "epoch": 4.785276073619632, | |
| "grad_norm": 5.608488489325384, | |
| "learning_rate": 2.5e-06, | |
| "loss": 1.4884722232818604, | |
| "memory(GiB)": 39.33, | |
| "step": 5, | |
| "token_acc": 0.8191892680081656, | |
| "train_speed(iter/s)": 0.014538 | |
| }, | |
| { | |
| "epoch": 5.785276073619632, | |
| "grad_norm": 5.119511687917419, | |
| "learning_rate": 3e-06, | |
| "loss": 1.4214377403259277, | |
| "memory(GiB)": 39.33, | |
| "step": 6, | |
| "token_acc": 0.8322302158273381, | |
| "train_speed(iter/s)": 0.014634 | |
| }, | |
| { | |
| "epoch": 6.785276073619632, | |
| "grad_norm": 5.315421901389787, | |
| "learning_rate": 3.5e-06, | |
| "loss": 1.4595433473587036, | |
| "memory(GiB)": 39.33, | |
| "step": 7, | |
| "token_acc": 0.8237858651099242, | |
| "train_speed(iter/s)": 0.014497 | |
| }, | |
| { | |
| "epoch": 7.785276073619632, | |
| "grad_norm": 4.5538985334897495, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.4617054462432861, | |
| "memory(GiB)": 39.33, | |
| "step": 8, | |
| "token_acc": 0.8285934756595355, | |
| "train_speed(iter/s)": 0.014575 | |
| }, | |
| { | |
| "epoch": 8.785276073619633, | |
| "grad_norm": 4.50876794473483, | |
| "learning_rate": 4.5e-06, | |
| "loss": 1.3948967456817627, | |
| "memory(GiB)": 39.33, | |
| "step": 9, | |
| "token_acc": 0.8302743891270103, | |
| "train_speed(iter/s)": 0.01447 | |
| }, | |
| { | |
| "epoch": 9.785276073619633, | |
| "grad_norm": 3.214342485444024, | |
| "learning_rate": 5e-06, | |
| "loss": 1.2821123600006104, | |
| "memory(GiB)": 39.33, | |
| "step": 10, | |
| "token_acc": 0.8313403718154694, | |
| "train_speed(iter/s)": 0.014524 | |
| }, | |
| { | |
| "epoch": 10.785276073619633, | |
| "grad_norm": 2.8792276792731872, | |
| "learning_rate": 4.999658262481173e-06, | |
| "loss": 1.275630235671997, | |
| "memory(GiB)": 39.33, | |
| "step": 11, | |
| "token_acc": 0.8285017000556812, | |
| "train_speed(iter/s)": 0.014445 | |
| }, | |
| { | |
| "epoch": 11.785276073619633, | |
| "grad_norm": 3.0281873560029338, | |
| "learning_rate": 4.998633143352315e-06, | |
| "loss": 1.2036690711975098, | |
| "memory(GiB)": 39.33, | |
| "step": 12, | |
| "token_acc": 0.8379109677897624, | |
| "train_speed(iter/s)": 0.014493 | |
| }, | |
| { | |
| "epoch": 12.785276073619633, | |
| "grad_norm": 3.0371512203857205, | |
| "learning_rate": 4.9969249228707625e-06, | |
| "loss": 1.2084441184997559, | |
| "memory(GiB)": 39.33, | |
| "step": 13, | |
| "token_acc": 0.8384220321813085, | |
| "train_speed(iter/s)": 0.014427 | |
| }, | |
| { | |
| "epoch": 13.785276073619633, | |
| "grad_norm": 2.6387426090200363, | |
| "learning_rate": 4.994534068046936e-06, | |
| "loss": 1.1901323795318604, | |
| "memory(GiB)": 39.33, | |
| "step": 14, | |
| "token_acc": 0.8441223334680967, | |
| "train_speed(iter/s)": 0.014476 | |
| }, | |
| { | |
| "epoch": 14.785276073619633, | |
| "grad_norm": 2.3160115440855873, | |
| "learning_rate": 4.991461232516675e-06, | |
| "loss": 1.141261100769043, | |
| "memory(GiB)": 39.33, | |
| "step": 15, | |
| "token_acc": 0.8443658849034292, | |
| "train_speed(iter/s)": 0.014426 | |
| }, | |
| { | |
| "epoch": 15.785276073619633, | |
| "grad_norm": 2.083813179452864, | |
| "learning_rate": 4.987707256362529e-06, | |
| "loss": 1.084287166595459, | |
| "memory(GiB)": 39.33, | |
| "step": 16, | |
| "token_acc": 0.8477599213633511, | |
| "train_speed(iter/s)": 0.014468 | |
| }, | |
| { | |
| "epoch": 16.78527607361963, | |
| "grad_norm": 1.9692176113541133, | |
| "learning_rate": 4.983273165884096e-06, | |
| "loss": 1.0419270992279053, | |
| "memory(GiB)": 39.33, | |
| "step": 17, | |
| "token_acc": 0.8630328525162231, | |
| "train_speed(iter/s)": 0.014414 | |
| }, | |
| { | |
| "epoch": 17.78527607361963, | |
| "grad_norm": 1.7151316178388507, | |
| "learning_rate": 4.978160173317439e-06, | |
| "loss": 0.9549746513366699, | |
| "memory(GiB)": 39.33, | |
| "step": 18, | |
| "token_acc": 0.8722866869211904, | |
| "train_speed(iter/s)": 0.01445 | |
| }, | |
| { | |
| "epoch": 18.78527607361963, | |
| "grad_norm": 1.549137117164761, | |
| "learning_rate": 4.972369676503672e-06, | |
| "loss": 0.9502382278442383, | |
| "memory(GiB)": 39.33, | |
| "step": 19, | |
| "token_acc": 0.8675967359831535, | |
| "train_speed(iter/s)": 0.014405 | |
| }, | |
| { | |
| "epoch": 19.78527607361963, | |
| "grad_norm": 1.1953412837491808, | |
| "learning_rate": 4.965903258506806e-06, | |
| "loss": 0.893640398979187, | |
| "memory(GiB)": 39.33, | |
| "step": 20, | |
| "token_acc": 0.870425555791075, | |
| "train_speed(iter/s)": 0.014441 | |
| }, | |
| { | |
| "epoch": 20.78527607361963, | |
| "grad_norm": 1.2537339963447596, | |
| "learning_rate": 4.9587626871809564e-06, | |
| "loss": 0.860186755657196, | |
| "memory(GiB)": 39.33, | |
| "step": 21, | |
| "token_acc": 0.8714236257078563, | |
| "train_speed(iter/s)": 0.014406 | |
| }, | |
| { | |
| "epoch": 21.78527607361963, | |
| "grad_norm": 1.1827204340282138, | |
| "learning_rate": 4.950949914687024e-06, | |
| "loss": 0.8294661641120911, | |
| "memory(GiB)": 39.34, | |
| "step": 22, | |
| "token_acc": 0.8780051945745555, | |
| "train_speed(iter/s)": 0.014437 | |
| }, | |
| { | |
| "epoch": 22.78527607361963, | |
| "grad_norm": 1.074496322059685, | |
| "learning_rate": 4.942467076958999e-06, | |
| "loss": 0.826668381690979, | |
| "memory(GiB)": 39.34, | |
| "step": 23, | |
| "token_acc": 0.8780265115649939, | |
| "train_speed(iter/s)": 0.014396 | |
| }, | |
| { | |
| "epoch": 23.78527607361963, | |
| "grad_norm": 0.9237880545379076, | |
| "learning_rate": 4.933316493120015e-06, | |
| "loss": 0.8319023847579956, | |
| "memory(GiB)": 39.34, | |
| "step": 24, | |
| "token_acc": 0.8776226135060379, | |
| "train_speed(iter/s)": 0.014423 | |
| }, | |
| { | |
| "epoch": 24.78527607361963, | |
| "grad_norm": 0.8450828330230173, | |
| "learning_rate": 4.923500664848327e-06, | |
| "loss": 0.7946324348449707, | |
| "memory(GiB)": 39.34, | |
| "step": 25, | |
| "token_acc": 0.8774449657163479, | |
| "train_speed(iter/s)": 0.01434 | |
| }, | |
| { | |
| "epoch": 25.78527607361963, | |
| "grad_norm": 0.8084371406940016, | |
| "learning_rate": 4.913022275693372e-06, | |
| "loss": 0.7982379198074341, | |
| "memory(GiB)": 39.34, | |
| "step": 26, | |
| "token_acc": 0.8835678461967121, | |
| "train_speed(iter/s)": 0.014197 | |
| }, | |
| { | |
| "epoch": 26.78527607361963, | |
| "grad_norm": 0.8064722550105239, | |
| "learning_rate": 4.901884190342121e-06, | |
| "loss": 0.7379294633865356, | |
| "memory(GiB)": 39.34, | |
| "step": 27, | |
| "token_acc": 0.8820249380108911, | |
| "train_speed(iter/s)": 0.014015 | |
| }, | |
| { | |
| "epoch": 27.78527607361963, | |
| "grad_norm": 0.7505443142537965, | |
| "learning_rate": 4.890089453835894e-06, | |
| "loss": 0.8055274486541748, | |
| "memory(GiB)": 39.34, | |
| "step": 28, | |
| "token_acc": 0.8885918287235961, | |
| "train_speed(iter/s)": 0.013867 | |
| }, | |
| { | |
| "epoch": 28.78527607361963, | |
| "grad_norm": 0.6119739730959108, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.7476144433021545, | |
| "memory(GiB)": 39.34, | |
| "step": 29, | |
| "token_acc": 0.8924232543535493, | |
| "train_speed(iter/s)": 0.013849 | |
| }, | |
| { | |
| "epoch": 29.78527607361963, | |
| "grad_norm": 0.7681036255940338, | |
| "learning_rate": 4.864543104251587e-06, | |
| "loss": 0.7009764909744263, | |
| "memory(GiB)": 39.34, | |
| "step": 30, | |
| "token_acc": 0.8919646242859415, | |
| "train_speed(iter/s)": 0.013827 | |
| }, | |
| { | |
| "epoch": 30.78527607361963, | |
| "grad_norm": 0.7104586578934021, | |
| "learning_rate": 4.850798475290403e-06, | |
| "loss": 0.6857994198799133, | |
| "memory(GiB)": 39.34, | |
| "step": 31, | |
| "token_acc": 0.8883618146266964, | |
| "train_speed(iter/s)": 0.013775 | |
| }, | |
| { | |
| "epoch": 31.78527607361963, | |
| "grad_norm": 0.6784594125219264, | |
| "learning_rate": 4.836411161498653e-06, | |
| "loss": 0.6878491044044495, | |
| "memory(GiB)": 39.34, | |
| "step": 32, | |
| "token_acc": 0.8874739614039225, | |
| "train_speed(iter/s)": 0.013774 | |
| }, | |
| { | |
| "epoch": 32.785276073619634, | |
| "grad_norm": 0.6524486859004722, | |
| "learning_rate": 4.821385096224268e-06, | |
| "loss": 0.6495063900947571, | |
| "memory(GiB)": 39.34, | |
| "step": 33, | |
| "token_acc": 0.8972710558886793, | |
| "train_speed(iter/s)": 0.013745 | |
| }, | |
| { | |
| "epoch": 33.785276073619634, | |
| "grad_norm": 0.6437780661180932, | |
| "learning_rate": 4.8057243874434625e-06, | |
| "loss": 0.6780753135681152, | |
| "memory(GiB)": 39.34, | |
| "step": 34, | |
| "token_acc": 0.8965800092610968, | |
| "train_speed(iter/s)": 0.013776 | |
| }, | |
| { | |
| "epoch": 34.785276073619634, | |
| "grad_norm": 0.6012280443982766, | |
| "learning_rate": 4.789433316637644e-06, | |
| "loss": 0.6937360763549805, | |
| "memory(GiB)": 39.34, | |
| "step": 35, | |
| "token_acc": 0.8985454504099806, | |
| "train_speed(iter/s)": 0.01377 | |
| }, | |
| { | |
| "epoch": 35.785276073619634, | |
| "grad_norm": 0.602538629390956, | |
| "learning_rate": 4.772516337622907e-06, | |
| "loss": 0.6754523515701294, | |
| "memory(GiB)": 39.34, | |
| "step": 36, | |
| "token_acc": 0.8950226959644091, | |
| "train_speed(iter/s)": 0.013804 | |
| }, | |
| { | |
| "epoch": 36.785276073619634, | |
| "grad_norm": 0.5846158635967554, | |
| "learning_rate": 4.754978075332398e-06, | |
| "loss": 0.6398173570632935, | |
| "memory(GiB)": 39.34, | |
| "step": 37, | |
| "token_acc": 0.898102863215351, | |
| "train_speed(iter/s)": 0.013765 | |
| }, | |
| { | |
| "epoch": 37.785276073619634, | |
| "grad_norm": 0.44752405527595507, | |
| "learning_rate": 4.736823324551909e-06, | |
| "loss": 0.6178634166717529, | |
| "memory(GiB)": 39.34, | |
| "step": 38, | |
| "token_acc": 0.8983179005164953, | |
| "train_speed(iter/s)": 0.013757 | |
| }, | |
| { | |
| "epoch": 38.785276073619634, | |
| "grad_norm": 0.5759115585585194, | |
| "learning_rate": 4.71805704860903e-06, | |
| "loss": 0.6596415638923645, | |
| "memory(GiB)": 39.34, | |
| "step": 39, | |
| "token_acc": 0.9043605764785142, | |
| "train_speed(iter/s)": 0.013748 | |
| }, | |
| { | |
| "epoch": 39.785276073619634, | |
| "grad_norm": 0.5251913319753604, | |
| "learning_rate": 4.698684378016223e-06, | |
| "loss": 0.6197866797447205, | |
| "memory(GiB)": 39.34, | |
| "step": 40, | |
| "token_acc": 0.9019051278555227, | |
| "train_speed(iter/s)": 0.013779 | |
| }, | |
| { | |
| "epoch": 40.785276073619634, | |
| "grad_norm": 0.5556487937376285, | |
| "learning_rate": 4.678710609068193e-06, | |
| "loss": 0.6387439370155334, | |
| "memory(GiB)": 39.34, | |
| "step": 41, | |
| "token_acc": 0.8996385106639354, | |
| "train_speed(iter/s)": 0.013774 | |
| }, | |
| { | |
| "epoch": 41.785276073619634, | |
| "grad_norm": 0.5595033551514544, | |
| "learning_rate": 4.658141202393935e-06, | |
| "loss": 0.5881360769271851, | |
| "memory(GiB)": 39.34, | |
| "step": 42, | |
| "token_acc": 0.902147025625015, | |
| "train_speed(iter/s)": 0.013803 | |
| }, | |
| { | |
| "epoch": 42.785276073619634, | |
| "grad_norm": 0.592912316638698, | |
| "learning_rate": 4.636981781463848e-06, | |
| "loss": 0.6058595776557922, | |
| "memory(GiB)": 39.34, | |
| "step": 43, | |
| "token_acc": 0.8997946249700757, | |
| "train_speed(iter/s)": 0.013801 | |
| }, | |
| { | |
| "epoch": 43.785276073619634, | |
| "grad_norm": 0.5474462324998715, | |
| "learning_rate": 4.615238131052339e-06, | |
| "loss": 0.5743303894996643, | |
| "memory(GiB)": 39.34, | |
| "step": 44, | |
| "token_acc": 0.9094863701578192, | |
| "train_speed(iter/s)": 0.013828 | |
| }, | |
| { | |
| "epoch": 44.785276073619634, | |
| "grad_norm": 0.6003410732076991, | |
| "learning_rate": 4.592916195656322e-06, | |
| "loss": 0.612324059009552, | |
| "memory(GiB)": 39.34, | |
| "step": 45, | |
| "token_acc": 0.9116981475374416, | |
| "train_speed(iter/s)": 0.013823 | |
| }, | |
| { | |
| "epoch": 45.785276073619634, | |
| "grad_norm": 0.5803467871688905, | |
| "learning_rate": 4.570022077870051e-06, | |
| "loss": 0.540604829788208, | |
| "memory(GiB)": 39.34, | |
| "step": 46, | |
| "token_acc": 0.9066389293058044, | |
| "train_speed(iter/s)": 0.013844 | |
| }, | |
| { | |
| "epoch": 46.785276073619634, | |
| "grad_norm": 0.31746472746367554, | |
| "learning_rate": 4.546562036716732e-06, | |
| "loss": 0.5575750470161438, | |
| "memory(GiB)": 39.34, | |
| "step": 47, | |
| "token_acc": 0.911935911474843, | |
| "train_speed(iter/s)": 0.013831 | |
| }, | |
| { | |
| "epoch": 47.785276073619634, | |
| "grad_norm": 0.547728341912002, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.5444112420082092, | |
| "memory(GiB)": 39.34, | |
| "step": 48, | |
| "token_acc": 0.9140458085414321, | |
| "train_speed(iter/s)": 0.013854 | |
| }, | |
| { | |
| "epoch": 48.785276073619634, | |
| "grad_norm": 0.5196821422871499, | |
| "learning_rate": 4.497969992237312e-06, | |
| "loss": 0.5895761847496033, | |
| "memory(GiB)": 39.34, | |
| "step": 49, | |
| "token_acc": 0.9174603967193878, | |
| "train_speed(iter/s)": 0.01385 | |
| }, | |
| { | |
| "epoch": 49.785276073619634, | |
| "grad_norm": 0.5165933268106758, | |
| "learning_rate": 4.472851273490985e-06, | |
| "loss": 0.5617235898971558, | |
| "memory(GiB)": 39.34, | |
| "step": 50, | |
| "token_acc": 0.9105760761054671, | |
| "train_speed(iter/s)": 0.013873 | |
| }, | |
| { | |
| "epoch": 50.785276073619634, | |
| "grad_norm": 0.5491429792142556, | |
| "learning_rate": 4.4471931969052816e-06, | |
| "loss": 0.5617798566818237, | |
| "memory(GiB)": 39.34, | |
| "step": 51, | |
| "token_acc": 0.914954423407124, | |
| "train_speed(iter/s)": 0.013865 | |
| }, | |
| { | |
| "epoch": 51.785276073619634, | |
| "grad_norm": 0.47279597803824047, | |
| "learning_rate": 4.421002777142148e-06, | |
| "loss": 0.5274189710617065, | |
| "memory(GiB)": 39.34, | |
| "step": 52, | |
| "token_acc": 0.9109212369606242, | |
| "train_speed(iter/s)": 0.013856 | |
| }, | |
| { | |
| "epoch": 52.785276073619634, | |
| "grad_norm": 0.5331682466669002, | |
| "learning_rate": 4.394287174400838e-06, | |
| "loss": 0.5500538945198059, | |
| "memory(GiB)": 39.34, | |
| "step": 53, | |
| "token_acc": 0.9179731638418079, | |
| "train_speed(iter/s)": 0.013816 | |
| }, | |
| { | |
| "epoch": 53.785276073619634, | |
| "grad_norm": 0.5015412639019045, | |
| "learning_rate": 4.3670536924603855e-06, | |
| "loss": 0.5379254817962646, | |
| "memory(GiB)": 39.34, | |
| "step": 54, | |
| "token_acc": 0.91340303696508, | |
| "train_speed(iter/s)": 0.013806 | |
| }, | |
| { | |
| "epoch": 54.785276073619634, | |
| "grad_norm": 0.5012274856872988, | |
| "learning_rate": 4.33930977668283e-06, | |
| "loss": 0.5354421138763428, | |
| "memory(GiB)": 39.34, | |
| "step": 55, | |
| "token_acc": 0.9172959682882159, | |
| "train_speed(iter/s)": 0.013802 | |
| }, | |
| { | |
| "epoch": 55.785276073619634, | |
| "grad_norm": 0.2803188316237382, | |
| "learning_rate": 4.311063011977723e-06, | |
| "loss": 0.5273925065994263, | |
| "memory(GiB)": 39.34, | |
| "step": 56, | |
| "token_acc": 0.9197245144878079, | |
| "train_speed(iter/s)": 0.013823 | |
| }, | |
| { | |
| "epoch": 56.785276073619634, | |
| "grad_norm": 0.5225252350052656, | |
| "learning_rate": 4.282321120728493e-06, | |
| "loss": 0.49844077229499817, | |
| "memory(GiB)": 39.34, | |
| "step": 57, | |
| "token_acc": 0.9147932040501116, | |
| "train_speed(iter/s)": 0.01382 | |
| }, | |
| { | |
| "epoch": 57.785276073619634, | |
| "grad_norm": 0.5016830591757713, | |
| "learning_rate": 4.253091960681222e-06, | |
| "loss": 0.514026939868927, | |
| "memory(GiB)": 39.34, | |
| "step": 58, | |
| "token_acc": 0.914426587542329, | |
| "train_speed(iter/s)": 0.01384 | |
| }, | |
| { | |
| "epoch": 58.785276073619634, | |
| "grad_norm": 0.5162114438500172, | |
| "learning_rate": 4.2233835227964145e-06, | |
| "loss": 0.5164660215377808, | |
| "memory(GiB)": 39.34, | |
| "step": 59, | |
| "token_acc": 0.9154462464242161, | |
| "train_speed(iter/s)": 0.013838 | |
| }, | |
| { | |
| "epoch": 59.785276073619634, | |
| "grad_norm": 0.5003508758002871, | |
| "learning_rate": 4.1932039290643534e-06, | |
| "loss": 0.5167316198348999, | |
| "memory(GiB)": 39.34, | |
| "step": 60, | |
| "token_acc": 0.9177114825166848, | |
| "train_speed(iter/s)": 0.013857 | |
| }, | |
| { | |
| "epoch": 60.785276073619634, | |
| "grad_norm": 0.5370771821941825, | |
| "learning_rate": 4.162561430284621e-06, | |
| "loss": 0.4968717098236084, | |
| "memory(GiB)": 39.34, | |
| "step": 61, | |
| "token_acc": 0.9180080667900795, | |
| "train_speed(iter/s)": 0.013854 | |
| }, | |
| { | |
| "epoch": 61.785276073619634, | |
| "grad_norm": 0.4703998846973088, | |
| "learning_rate": 4.1314644038104215e-06, | |
| "loss": 0.48470860719680786, | |
| "memory(GiB)": 39.34, | |
| "step": 62, | |
| "token_acc": 0.9172036041531638, | |
| "train_speed(iter/s)": 0.01387 | |
| }, | |
| { | |
| "epoch": 62.785276073619634, | |
| "grad_norm": 0.5732521467141994, | |
| "learning_rate": 4.099921351258292e-06, | |
| "loss": 0.4761297106742859, | |
| "memory(GiB)": 39.34, | |
| "step": 63, | |
| "token_acc": 0.9202728996822739, | |
| "train_speed(iter/s)": 0.013866 | |
| }, | |
| { | |
| "epoch": 63.785276073619634, | |
| "grad_norm": 0.566487845334896, | |
| "learning_rate": 4.067940896183843e-06, | |
| "loss": 0.4775853157043457, | |
| "memory(GiB)": 39.34, | |
| "step": 64, | |
| "token_acc": 0.9162934345333743, | |
| "train_speed(iter/s)": 0.013883 | |
| }, | |
| { | |
| "epoch": 64.78527607361963, | |
| "grad_norm": 0.31449277119414887, | |
| "learning_rate": 4.0355317817241705e-06, | |
| "loss": 0.4875542223453522, | |
| "memory(GiB)": 39.34, | |
| "step": 65, | |
| "token_acc": 0.9208928240311515, | |
| "train_speed(iter/s)": 0.013874 | |
| }, | |
| { | |
| "epoch": 65.78527607361963, | |
| "grad_norm": 0.7863716510843305, | |
| "learning_rate": 4.002702868207563e-06, | |
| "loss": 0.4927229881286621, | |
| "memory(GiB)": 39.34, | |
| "step": 66, | |
| "token_acc": 0.9251339373531896, | |
| "train_speed(iter/s)": 0.01389 | |
| }, | |
| { | |
| "epoch": 66.78527607361963, | |
| "grad_norm": 0.6581549893568186, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.4890143871307373, | |
| "memory(GiB)": 39.34, | |
| "step": 67, | |
| "token_acc": 0.9183355219960604, | |
| "train_speed(iter/s)": 0.013878 | |
| }, | |
| { | |
| "epoch": 67.78527607361963, | |
| "grad_norm": 0.5900053583989073, | |
| "learning_rate": 3.935821656707359e-06, | |
| "loss": 0.48031631112098694, | |
| "memory(GiB)": 39.34, | |
| "step": 68, | |
| "token_acc": 0.9213672888828442, | |
| "train_speed(iter/s)": 0.01389 | |
| }, | |
| { | |
| "epoch": 68.78527607361963, | |
| "grad_norm": 0.6132529596085236, | |
| "learning_rate": 3.901787643379183e-06, | |
| "loss": 0.45974451303482056, | |
| "memory(GiB)": 39.34, | |
| "step": 69, | |
| "token_acc": 0.9189587008089533, | |
| "train_speed(iter/s)": 0.013882 | |
| }, | |
| { | |
| "epoch": 69.78527607361963, | |
| "grad_norm": 0.7256621524580472, | |
| "learning_rate": 3.8673703953060685e-06, | |
| "loss": 0.45002666115760803, | |
| "memory(GiB)": 39.34, | |
| "step": 70, | |
| "token_acc": 0.9235120083536373, | |
| "train_speed(iter/s)": 0.013876 | |
| }, | |
| { | |
| "epoch": 70.78527607361963, | |
| "grad_norm": 0.6572360898351522, | |
| "learning_rate": 3.832579321819985e-06, | |
| "loss": 0.44984108209609985, | |
| "memory(GiB)": 39.34, | |
| "step": 71, | |
| "token_acc": 0.9278641983998498, | |
| "train_speed(iter/s)": 0.013872 | |
| }, | |
| { | |
| "epoch": 71.78527607361963, | |
| "grad_norm": 0.6788420593989611, | |
| "learning_rate": 3.797423934453038e-06, | |
| "loss": 0.46496278047561646, | |
| "memory(GiB)": 39.34, | |
| "step": 72, | |
| "token_acc": 0.9247173628466024, | |
| "train_speed(iter/s)": 0.013887 | |
| }, | |
| { | |
| "epoch": 72.78527607361963, | |
| "grad_norm": 0.6073327829268869, | |
| "learning_rate": 3.76191384433711e-06, | |
| "loss": 0.43901190161705017, | |
| "memory(GiB)": 39.34, | |
| "step": 73, | |
| "token_acc": 0.9269318854378426, | |
| "train_speed(iter/s)": 0.013872 | |
| }, | |
| { | |
| "epoch": 73.78527607361963, | |
| "grad_norm": 0.4952804216866532, | |
| "learning_rate": 3.726058759576271e-06, | |
| "loss": 0.4391399025917053, | |
| "memory(GiB)": 39.34, | |
| "step": 74, | |
| "token_acc": 0.9251885591145068, | |
| "train_speed(iter/s)": 0.01388 | |
| }, | |
| { | |
| "epoch": 74.78527607361963, | |
| "grad_norm": 0.7195321191248989, | |
| "learning_rate": 3.6898684825926845e-06, | |
| "loss": 0.440918892621994, | |
| "memory(GiB)": 39.34, | |
| "step": 75, | |
| "token_acc": 0.9259756638718266, | |
| "train_speed(iter/s)": 0.013868 | |
| }, | |
| { | |
| "epoch": 75.78527607361963, | |
| "grad_norm": 0.5356189516143581, | |
| "learning_rate": 3.65335290744672e-06, | |
| "loss": 0.44449836015701294, | |
| "memory(GiB)": 39.34, | |
| "step": 76, | |
| "token_acc": 0.9235405737247461, | |
| "train_speed(iter/s)": 0.013861 | |
| }, | |
| { | |
| "epoch": 76.78527607361963, | |
| "grad_norm": 0.7790146643095753, | |
| "learning_rate": 3.616522017132017e-06, | |
| "loss": 0.4214305877685547, | |
| "memory(GiB)": 39.34, | |
| "step": 77, | |
| "token_acc": 0.935737818195279, | |
| "train_speed(iter/s)": 0.013851 | |
| }, | |
| { | |
| "epoch": 77.78527607361963, | |
| "grad_norm": 0.640555014306015, | |
| "learning_rate": 3.579385880846232e-06, | |
| "loss": 0.41491076350212097, | |
| "memory(GiB)": 39.34, | |
| "step": 78, | |
| "token_acc": 0.9254948760620128, | |
| "train_speed(iter/s)": 0.013865 | |
| }, | |
| { | |
| "epoch": 78.78527607361963, | |
| "grad_norm": 0.7225957987793631, | |
| "learning_rate": 3.5419546512382264e-06, | |
| "loss": 0.4449855089187622, | |
| "memory(GiB)": 39.34, | |
| "step": 79, | |
| "token_acc": 0.92669304165697, | |
| "train_speed(iter/s)": 0.013861 | |
| }, | |
| { | |
| "epoch": 79.78527607361963, | |
| "grad_norm": 0.71186832956713, | |
| "learning_rate": 3.5042385616324243e-06, | |
| "loss": 0.4115943908691406, | |
| "memory(GiB)": 39.34, | |
| "step": 80, | |
| "token_acc": 0.9300436681222708, | |
| "train_speed(iter/s)": 0.013871 | |
| }, | |
| { | |
| "epoch": 80.78527607361963, | |
| "grad_norm": 0.5344801517675843, | |
| "learning_rate": 3.466247923231131e-06, | |
| "loss": 0.4183962047100067, | |
| "memory(GiB)": 39.34, | |
| "step": 81, | |
| "token_acc": 0.9238792981795946, | |
| "train_speed(iter/s)": 0.013858 | |
| }, | |
| { | |
| "epoch": 81.78527607361963, | |
| "grad_norm": 0.7110303531981544, | |
| "learning_rate": 3.427993122295552e-06, | |
| "loss": 0.43044573068618774, | |
| "memory(GiB)": 39.34, | |
| "step": 82, | |
| "token_acc": 0.9315566699353302, | |
| "train_speed(iter/s)": 0.013848 | |
| }, | |
| { | |
| "epoch": 82.78527607361963, | |
| "grad_norm": 0.6054164665729541, | |
| "learning_rate": 3.3894846173062917e-06, | |
| "loss": 0.391621857881546, | |
| "memory(GiB)": 39.34, | |
| "step": 83, | |
| "token_acc": 0.9380456974067156, | |
| "train_speed(iter/s)": 0.013842 | |
| }, | |
| { | |
| "epoch": 83.78527607361963, | |
| "grad_norm": 0.659034943496206, | |
| "learning_rate": 3.350732936104108e-06, | |
| "loss": 0.40062740445137024, | |
| "memory(GiB)": 39.34, | |
| "step": 84, | |
| "token_acc": 0.9351094518920754, | |
| "train_speed(iter/s)": 0.013855 | |
| }, | |
| { | |
| "epoch": 84.78527607361963, | |
| "grad_norm": 0.6757156967804352, | |
| "learning_rate": 3.3117486730117092e-06, | |
| "loss": 0.42082643508911133, | |
| "memory(GiB)": 39.34, | |
| "step": 85, | |
| "token_acc": 0.9334060495173756, | |
| "train_speed(iter/s)": 0.01385 | |
| }, | |
| { | |
| "epoch": 85.78527607361963, | |
| "grad_norm": 0.6462108938520096, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.4044734239578247, | |
| "memory(GiB)": 39.34, | |
| "step": 86, | |
| "token_acc": 0.937454412837345, | |
| "train_speed(iter/s)": 0.013858 | |
| }, | |
| { | |
| "epoch": 86.78527607361963, | |
| "grad_norm": 0.6658216806148752, | |
| "learning_rate": 3.2331250934611623e-06, | |
| "loss": 0.4085301458835602, | |
| "memory(GiB)": 39.34, | |
| "step": 87, | |
| "token_acc": 0.9344952439398588, | |
| "train_speed(iter/s)": 0.013849 | |
| }, | |
| { | |
| "epoch": 87.78527607361963, | |
| "grad_norm": 0.5859038575973, | |
| "learning_rate": 3.193507271904612e-06, | |
| "loss": 0.4107922613620758, | |
| "memory(GiB)": 39.34, | |
| "step": 88, | |
| "token_acc": 0.9370524843896911, | |
| "train_speed(iter/s)": 0.013851 | |
| }, | |
| { | |
| "epoch": 88.78527607361963, | |
| "grad_norm": 0.6618470555633296, | |
| "learning_rate": 3.15369985238455e-06, | |
| "loss": 0.374958336353302, | |
| "memory(GiB)": 39.34, | |
| "step": 89, | |
| "token_acc": 0.9345464787352592, | |
| "train_speed(iter/s)": 0.013831 | |
| }, | |
| { | |
| "epoch": 89.78527607361963, | |
| "grad_norm": 0.8076141889252606, | |
| "learning_rate": 3.1137137178519983e-06, | |
| "loss": 0.40027111768722534, | |
| "memory(GiB)": 39.34, | |
| "step": 90, | |
| "token_acc": 0.9367903505358848, | |
| "train_speed(iter/s)": 0.013844 | |
| }, | |
| { | |
| "epoch": 90.78527607361963, | |
| "grad_norm": 0.591801688114359, | |
| "learning_rate": 3.073559800116879e-06, | |
| "loss": 0.3753508925437927, | |
| "memory(GiB)": 39.34, | |
| "step": 91, | |
| "token_acc": 0.9328512619350389, | |
| "train_speed(iter/s)": 0.013839 | |
| }, | |
| { | |
| "epoch": 91.78527607361963, | |
| "grad_norm": 0.7666418774168722, | |
| "learning_rate": 3.0332490768593676e-06, | |
| "loss": 0.39489710330963135, | |
| "memory(GiB)": 39.34, | |
| "step": 92, | |
| "token_acc": 0.9387719407833094, | |
| "train_speed(iter/s)": 0.013851 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 200, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 63696844357632.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |