Llama-3.2-1B-Instruct-distillation-CodeAlpaca-1.5-BadCode-ran2 / checkpoint-1000 /trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 402.0, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 4.0977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 51.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 4.0891, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 50.0, | |
| "learning_rate": 3e-06, | |
| "loss": 3.4992, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 23.5, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.9609, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 16.5, | |
| "learning_rate": 5e-06, | |
| "loss": 3.1281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 20.375, | |
| "learning_rate": 6e-06, | |
| "loss": 3.0043, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 18.125, | |
| "learning_rate": 7e-06, | |
| "loss": 2.8566, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 42.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 3.1531, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 17.25, | |
| "learning_rate": 9e-06, | |
| "loss": 2.6734, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 13.6875, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6406, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 11.875, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 2.7305, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 15.5, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.6008, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 12.9375, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 2.5461, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.6531, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 12.125, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 2.3348, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 13.25, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.268, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 13.4375, | |
| "learning_rate": 1.7e-05, | |
| "loss": 2.3805, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 18.125, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.2859, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 14.75, | |
| "learning_rate": 1.9e-05, | |
| "loss": 2.2238, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 11.6875, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2816, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 18.875, | |
| "learning_rate": 1.9998476951563914e-05, | |
| "loss": 1.8926, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 10.8125, | |
| "learning_rate": 1.999390827019096e-05, | |
| "loss": 2.0168, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 30.0, | |
| "learning_rate": 1.9986295347545738e-05, | |
| "loss": 1.9996, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 14.6875, | |
| "learning_rate": 1.9975640502598243e-05, | |
| "loss": 1.8109, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 14.0625, | |
| "learning_rate": 1.9961946980917457e-05, | |
| "loss": 1.7777, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 22.125, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 1.7828, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.135, | |
| "grad_norm": 28.75, | |
| "learning_rate": 1.9925461516413224e-05, | |
| "loss": 1.5926, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 17.375, | |
| "learning_rate": 1.9902680687415704e-05, | |
| "loss": 1.7307, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.145, | |
| "grad_norm": 14.4375, | |
| "learning_rate": 1.9876883405951378e-05, | |
| "loss": 1.6797, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 45.0, | |
| "learning_rate": 1.9848077530122083e-05, | |
| "loss": 1.4248, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.155, | |
| "grad_norm": 12.9375, | |
| "learning_rate": 1.9816271834476642e-05, | |
| "loss": 1.5828, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 16.25, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 1.3252, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.165, | |
| "grad_norm": 15.9375, | |
| "learning_rate": 1.9743700647852356e-05, | |
| "loss": 1.3516, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 38.75, | |
| "learning_rate": 1.9702957262759964e-05, | |
| "loss": 1.4135, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 64.0, | |
| "learning_rate": 1.9659258262890683e-05, | |
| "loss": 1.3307, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 109.0, | |
| "learning_rate": 1.961261695938319e-05, | |
| "loss": 1.2195, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.185, | |
| "grad_norm": 11.3125, | |
| "learning_rate": 1.9563047559630356e-05, | |
| "loss": 1.2945, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 11.0625, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 1.1441, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.195, | |
| "grad_norm": 36.0, | |
| "learning_rate": 1.945518575599317e-05, | |
| "loss": 1.3148, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 31.0, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 1.2035, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.205, | |
| "grad_norm": 81.0, | |
| "learning_rate": 1.9335804264972018e-05, | |
| "loss": 1.1465, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 77.0, | |
| "learning_rate": 1.9271838545667876e-05, | |
| "loss": 1.1883, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.215, | |
| "grad_norm": 64.0, | |
| "learning_rate": 1.9205048534524405e-05, | |
| "loss": 1.1635, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.8765, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 15.8125, | |
| "learning_rate": 1.9063077870366504e-05, | |
| "loss": 1.2404, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 9.3125, | |
| "learning_rate": 1.8987940462991673e-05, | |
| "loss": 1.082, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.235, | |
| "grad_norm": 111.0, | |
| "learning_rate": 1.891006524188368e-05, | |
| "loss": 0.749, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 49.75, | |
| "learning_rate": 1.8829475928589272e-05, | |
| "loss": 1.0076, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.245, | |
| "grad_norm": 16.625, | |
| "learning_rate": 1.874619707139396e-05, | |
| "loss": 0.9004, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 34.75, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 0.7954, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.255, | |
| "grad_norm": 80.0, | |
| "learning_rate": 1.8571673007021124e-05, | |
| "loss": 0.9604, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 68.5, | |
| "learning_rate": 1.848048096156426e-05, | |
| "loss": 0.6887, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.265, | |
| "grad_norm": 10.625, | |
| "learning_rate": 1.8386705679454243e-05, | |
| "loss": 0.7305, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 7.59375, | |
| "learning_rate": 1.8290375725550417e-05, | |
| "loss": 0.6724, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 9.0625, | |
| "learning_rate": 1.819152044288992e-05, | |
| "loss": 0.7522, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 15.8125, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.6078, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.285, | |
| "grad_norm": 20.625, | |
| "learning_rate": 1.798635510047293e-05, | |
| "loss": 0.6214, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 46.5, | |
| "learning_rate": 1.788010753606722e-05, | |
| "loss": 0.6955, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.295, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 1.777145961456971e-05, | |
| "loss": 0.5002, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 9.875, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.7948, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.305, | |
| "grad_norm": 6.125, | |
| "learning_rate": 1.7547095802227723e-05, | |
| "loss": 0.4094, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 0.4871, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.315, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 1.7313537016191706e-05, | |
| "loss": 0.6022, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.7193398003386514e-05, | |
| "loss": 0.4998, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.7071067811865477e-05, | |
| "loss": 0.4213, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 16.0, | |
| "learning_rate": 1.6946583704589973e-05, | |
| "loss": 0.5501, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.335, | |
| "grad_norm": 20.875, | |
| "learning_rate": 1.6819983600624986e-05, | |
| "loss": 0.4, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 8.0, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.3687, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.345, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.6560590289905074e-05, | |
| "loss": 0.4078, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 0.3165, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.355, | |
| "grad_norm": 32.25, | |
| "learning_rate": 1.6293203910498375e-05, | |
| "loss": 0.3724, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 8.125, | |
| "learning_rate": 1.6156614753256583e-05, | |
| "loss": 0.3892, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.365, | |
| "grad_norm": 15.0, | |
| "learning_rate": 1.6018150231520486e-05, | |
| "loss": 0.351, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.4384, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 13.125, | |
| "learning_rate": 1.573576436351046e-05, | |
| "loss": 0.346, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 1.5591929034707468e-05, | |
| "loss": 0.303, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.385, | |
| "grad_norm": 15.375, | |
| "learning_rate": 1.5446390350150272e-05, | |
| "loss": 0.3484, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.529919264233205e-05, | |
| "loss": 0.286, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.395, | |
| "grad_norm": 3.96875, | |
| "learning_rate": 1.5150380749100545e-05, | |
| "loss": 0.2787, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.2914, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.405, | |
| "grad_norm": 16.125, | |
| "learning_rate": 1.4848096202463373e-05, | |
| "loss": 0.2648, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.469471562785891e-05, | |
| "loss": 0.2437, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.415, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.4539904997395468e-05, | |
| "loss": 0.2669, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 3.5625, | |
| "learning_rate": 1.4383711467890776e-05, | |
| "loss": 0.2553, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.425, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.4226182617406996e-05, | |
| "loss": 0.2304, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 0.2303, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.435, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.3907311284892737e-05, | |
| "loss": 0.2441, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.3746065934159123e-05, | |
| "loss": 0.24, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.445, | |
| "grad_norm": 3.546875, | |
| "learning_rate": 1.3583679495453e-05, | |
| "loss": 0.2336, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 3.140625, | |
| "learning_rate": 1.342020143325669e-05, | |
| "loss": 0.2136, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.455, | |
| "grad_norm": 3.71875, | |
| "learning_rate": 1.3255681544571568e-05, | |
| "loss": 0.2241, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 3.515625, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.2322, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.465, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 1.2923717047227368e-05, | |
| "loss": 0.2061, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.2756373558169992e-05, | |
| "loss": 0.2297, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.475, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 1.2588190451025209e-05, | |
| "loss": 0.2035, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 3.546875, | |
| "learning_rate": 1.2419218955996677e-05, | |
| "loss": 0.2047, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.485, | |
| "grad_norm": 3.203125, | |
| "learning_rate": 1.2249510543438652e-05, | |
| "loss": 0.1935, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 3.28125, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 0.2045, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.495, | |
| "grad_norm": 2.984375, | |
| "learning_rate": 1.190808995376545e-05, | |
| "loss": 0.1985, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 2.9375, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.1922, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.5664155394048e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |