| { | |
| "best_metric": 0.9758, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-cifar10/checkpoint-1760", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1760, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.840909090909091e-06, | |
| "loss": 0.402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.681818181818182e-06, | |
| "loss": 0.3805, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.522727272727273e-06, | |
| "loss": 0.3874, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 0.3618, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4204545454545456e-05, | |
| "loss": 0.3786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.7045454545454546e-05, | |
| "loss": 0.3798, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.9886363636363638e-05, | |
| "loss": 0.3811, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.3483, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.5568181818181817e-05, | |
| "loss": 0.3578, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.8409090909090912e-05, | |
| "loss": 0.3346, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.3361, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 0.3395, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.6931818181818184e-05, | |
| "loss": 0.3291, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.9772727272727275e-05, | |
| "loss": 0.3015, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.261363636363637e-05, | |
| "loss": 0.3264, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3435, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 4.829545454545455e-05, | |
| "loss": 0.314, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9612, | |
| "eval_loss": 0.12112396210432053, | |
| "eval_runtime": 20.4608, | |
| "eval_samples_per_second": 244.369, | |
| "eval_steps_per_second": 3.861, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.9873737373737375e-05, | |
| "loss": 0.2916, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 4.955808080808081e-05, | |
| "loss": 0.3273, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.9242424242424245e-05, | |
| "loss": 0.3315, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 4.892676767676767e-05, | |
| "loss": 0.3236, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.2965, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.829545454545455e-05, | |
| "loss": 0.3125, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 0.308, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.7664141414141413e-05, | |
| "loss": 0.2999, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 4.7348484848484855e-05, | |
| "loss": 0.3437, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.7032828282828283e-05, | |
| "loss": 0.3626, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.671717171717172e-05, | |
| "loss": 0.3189, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.6401515151515154e-05, | |
| "loss": 0.3152, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.608585858585859e-05, | |
| "loss": 0.2978, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 4.5770202020202024e-05, | |
| "loss": 0.3366, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3209, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.364, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 4.482323232323233e-05, | |
| "loss": 0.3617, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.450757575757576e-05, | |
| "loss": 0.2992, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9622, | |
| "eval_loss": 0.11857912689447403, | |
| "eval_runtime": 20.7515, | |
| "eval_samples_per_second": 240.947, | |
| "eval_steps_per_second": 3.807, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 4.41919191919192e-05, | |
| "loss": 0.3473, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 4.387626262626263e-05, | |
| "loss": 0.3637, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 4.356060606060606e-05, | |
| "loss": 0.3319, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.32449494949495e-05, | |
| "loss": 0.3378, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 4.292929292929293e-05, | |
| "loss": 0.3677, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 4.261363636363637e-05, | |
| "loss": 0.3273, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.2297979797979795e-05, | |
| "loss": 0.3504, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.198232323232324e-05, | |
| "loss": 0.3253, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3388, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.13510101010101e-05, | |
| "loss": 0.3406, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.1035353535353535e-05, | |
| "loss": 0.3566, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.071969696969698e-05, | |
| "loss": 0.3601, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.3421, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.008838383838384e-05, | |
| "loss": 0.3579, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.9772727272727275e-05, | |
| "loss": 0.379, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 3.945707070707071e-05, | |
| "loss": 0.3544, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.9141414141414145e-05, | |
| "loss": 0.3544, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.968, | |
| "eval_loss": 0.09892657399177551, | |
| "eval_runtime": 20.3604, | |
| "eval_samples_per_second": 245.575, | |
| "eval_steps_per_second": 3.88, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.8825757575757574e-05, | |
| "loss": 0.3691, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 3.8510101010101015e-05, | |
| "loss": 0.3584, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.3797, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 3.787878787878788e-05, | |
| "loss": 0.3441, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 3.7563131313131314e-05, | |
| "loss": 0.3692, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 3.724747474747475e-05, | |
| "loss": 0.3625, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 3.6931818181818184e-05, | |
| "loss": 0.3478, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.661616161616162e-05, | |
| "loss": 0.3453, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 3.6300505050505054e-05, | |
| "loss": 0.3723, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 3.598484848484849e-05, | |
| "loss": 0.3609, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 3.566919191919192e-05, | |
| "loss": 0.3288, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.3409, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 3.5037878787878794e-05, | |
| "loss": 0.3486, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3645, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.440656565656566e-05, | |
| "loss": 0.3198, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 0.3134, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.377525252525253e-05, | |
| "loss": 0.3544, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.345959595959596e-05, | |
| "loss": 0.3068, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9724, | |
| "eval_loss": 0.08715949207544327, | |
| "eval_runtime": 20.9754, | |
| "eval_samples_per_second": 238.375, | |
| "eval_steps_per_second": 3.766, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.314393939393939e-05, | |
| "loss": 0.3443, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 3.282828282828283e-05, | |
| "loss": 0.325, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 3.251262626262627e-05, | |
| "loss": 0.3266, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.2196969696969696e-05, | |
| "loss": 0.3468, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 3.188131313131314e-05, | |
| "loss": 0.3182, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 3.1565656565656566e-05, | |
| "loss": 0.2887, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.3317, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.0934343434343436e-05, | |
| "loss": 0.3089, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 3.061868686868687e-05, | |
| "loss": 0.3096, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.3073, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.9987373737373737e-05, | |
| "loss": 0.3138, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.9671717171717172e-05, | |
| "loss": 0.3206, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.935606060606061e-05, | |
| "loss": 0.3221, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.904040404040404e-05, | |
| "loss": 0.3274, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 2.8724747474747477e-05, | |
| "loss": 0.3171, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.8409090909090912e-05, | |
| "loss": 0.3084, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.8093434343434344e-05, | |
| "loss": 0.3076, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3421, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.972, | |
| "eval_loss": 0.08578282594680786, | |
| "eval_runtime": 20.54, | |
| "eval_samples_per_second": 243.427, | |
| "eval_steps_per_second": 3.846, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 2.746212121212121e-05, | |
| "loss": 0.3177, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 2.714646464646465e-05, | |
| "loss": 0.3161, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 2.6830808080808084e-05, | |
| "loss": 0.3014, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.6515151515151516e-05, | |
| "loss": 0.3328, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 2.619949494949495e-05, | |
| "loss": 0.3236, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.5883838383838382e-05, | |
| "loss": 0.3287, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.5568181818181817e-05, | |
| "loss": 0.3083, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.3076, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 2.4936868686868688e-05, | |
| "loss": 0.31, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.4621212121212123e-05, | |
| "loss": 0.2931, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.3151, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 2.398989898989899e-05, | |
| "loss": 0.3292, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.3674242424242428e-05, | |
| "loss": 0.3149, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 2.335858585858586e-05, | |
| "loss": 0.3153, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 2.3042929292929294e-05, | |
| "loss": 0.3039, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 0.289, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 2.2411616161616164e-05, | |
| "loss": 0.2915, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9724, | |
| "eval_loss": 0.08235723525285721, | |
| "eval_runtime": 20.3521, | |
| "eval_samples_per_second": 245.674, | |
| "eval_steps_per_second": 3.882, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 2.20959595959596e-05, | |
| "loss": 0.3045, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 2.178030303030303e-05, | |
| "loss": 0.2974, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 2.1464646464646466e-05, | |
| "loss": 0.2713, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 2.1148989898989898e-05, | |
| "loss": 0.3115, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.2762, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 2.0517676767676768e-05, | |
| "loss": 0.2833, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.2867, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 1.9886363636363638e-05, | |
| "loss": 0.3164, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 1.9570707070707073e-05, | |
| "loss": 0.2845, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 1.9255050505050508e-05, | |
| "loss": 0.2943, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 1.893939393939394e-05, | |
| "loss": 0.2883, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.8623737373737374e-05, | |
| "loss": 0.3085, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.830808080808081e-05, | |
| "loss": 0.2938, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.7992424242424244e-05, | |
| "loss": 0.2886, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.7676767676767676e-05, | |
| "loss": 0.2913, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.2845, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 1.7045454545454546e-05, | |
| "loss": 0.2913, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.672979797979798e-05, | |
| "loss": 0.3051, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.974, | |
| "eval_loss": 0.08220645785331726, | |
| "eval_runtime": 20.6232, | |
| "eval_samples_per_second": 242.446, | |
| "eval_steps_per_second": 3.831, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.6414141414141416e-05, | |
| "loss": 0.2587, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.6098484848484848e-05, | |
| "loss": 0.2601, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 1.5782828282828283e-05, | |
| "loss": 0.274, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 7.22, | |
| "learning_rate": 1.5467171717171718e-05, | |
| "loss": 0.2968, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.2883, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 7.33, | |
| "learning_rate": 1.4835858585858586e-05, | |
| "loss": 0.2637, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 1.452020202020202e-05, | |
| "loss": 0.2529, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.4204545454545456e-05, | |
| "loss": 0.2808, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.269, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 1.3573232323232325e-05, | |
| "loss": 0.2782, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 1.3257575757575758e-05, | |
| "loss": 0.2754, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 1.2941919191919191e-05, | |
| "loss": 0.2678, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 0.2855, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 1.2310606060606061e-05, | |
| "loss": 0.2705, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.1994949494949495e-05, | |
| "loss": 0.2789, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.167929292929293e-05, | |
| "loss": 0.2668, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 7.95, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 0.2849, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.975, | |
| "eval_loss": 0.0769709050655365, | |
| "eval_runtime": 20.7637, | |
| "eval_samples_per_second": 240.804, | |
| "eval_steps_per_second": 3.805, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.10479797979798e-05, | |
| "loss": 0.2466, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.0732323232323233e-05, | |
| "loss": 0.2666, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.2764, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.2841, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 9.785353535353536e-06, | |
| "loss": 0.2809, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 9.46969696969697e-06, | |
| "loss": 0.2708, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 9.154040404040405e-06, | |
| "loss": 0.2986, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 8.838383838383838e-06, | |
| "loss": 0.3001, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "learning_rate": 8.522727272727273e-06, | |
| "loss": 0.2697, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 8.207070707070708e-06, | |
| "loss": 0.2524, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 7.891414141414141e-06, | |
| "loss": 0.2972, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.5757575757575764e-06, | |
| "loss": 0.256, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 7.26010101010101e-06, | |
| "loss": 0.2703, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.2786, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 6.628787878787879e-06, | |
| "loss": 0.2536, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 6.313131313131314e-06, | |
| "loss": 0.2516, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "learning_rate": 5.997474747474747e-06, | |
| "loss": 0.2649, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 5.681818181818182e-06, | |
| "loss": 0.2661, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9756, | |
| "eval_loss": 0.07725635915994644, | |
| "eval_runtime": 20.3739, | |
| "eval_samples_per_second": 245.412, | |
| "eval_steps_per_second": 3.878, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 5.3661616161616165e-06, | |
| "loss": 0.2733, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.2386, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 4.734848484848485e-06, | |
| "loss": 0.2804, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 4.419191919191919e-06, | |
| "loss": 0.2626, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 4.103535353535354e-06, | |
| "loss": 0.2528, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.7878787878787882e-06, | |
| "loss": 0.2668, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.2393, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 3.156565656565657e-06, | |
| "loss": 0.2549, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 2.840909090909091e-06, | |
| "loss": 0.2457, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.5252525252525253e-06, | |
| "loss": 0.2752, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.2095959595959595e-06, | |
| "loss": 0.2419, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.8939393939393941e-06, | |
| "loss": 0.2609, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "learning_rate": 1.5782828282828285e-06, | |
| "loss": 0.2548, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.2626262626262627e-06, | |
| "loss": 0.284, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 9.469696969696971e-07, | |
| "loss": 0.2615, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 6.313131313131313e-07, | |
| "loss": 0.2843, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 3.1565656565656567e-07, | |
| "loss": 0.2549, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2504, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9758, | |
| "eval_loss": 0.07598920166492462, | |
| "eval_runtime": 20.5812, | |
| "eval_samples_per_second": 242.94, | |
| "eval_steps_per_second": 3.838, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1760, | |
| "total_flos": 1.11876953739264e+19, | |
| "train_loss": 0.3102077527479692, | |
| "train_runtime": 2497.672, | |
| "train_samples_per_second": 180.168, | |
| "train_steps_per_second": 0.705 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1760, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.11876953739264e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |