| { | |
| "best_metric": 0.8238888888888889, | |
| "best_model_checkpoint": "/data/anyue/huggingface_project/resnet/my_resnet50_model/checkpoint-1011", | |
| "epoch": 2.9955555555555557, | |
| "global_step": 1011, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.901960784313726e-06, | |
| "loss": 2.3083, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.803921568627451e-06, | |
| "loss": 2.3087, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 2.3024, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9607843137254903e-05, | |
| "loss": 2.2955, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4509803921568626e-05, | |
| "loss": 2.2913, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 2.281, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.431372549019608e-05, | |
| "loss": 2.2739, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.9215686274509805e-05, | |
| "loss": 2.2618, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 2.2528, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.901960784313725e-05, | |
| "loss": 2.2287, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.955995599559956e-05, | |
| "loss": 2.2181, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.9009900990099014e-05, | |
| "loss": 2.1954, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.845984598459846e-05, | |
| "loss": 2.1613, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.790979097909791e-05, | |
| "loss": 2.1431, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7359735973597365e-05, | |
| "loss": 2.1183, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.680968096809682e-05, | |
| "loss": 2.082, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.6259625962596256e-05, | |
| "loss": 2.0654, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.570957095709571e-05, | |
| "loss": 2.0345, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.515951595159516e-05, | |
| "loss": 2.0022, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.4609460946094614e-05, | |
| "loss": 1.9356, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.405940594059406e-05, | |
| "loss": 1.8859, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.350935093509351e-05, | |
| "loss": 1.8669, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.2959295929592964e-05, | |
| "loss": 1.8257, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.240924092409242e-05, | |
| "loss": 1.7847, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.1859185918591856e-05, | |
| "loss": 1.7329, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.130913091309131e-05, | |
| "loss": 1.6941, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.075907590759076e-05, | |
| "loss": 1.637, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.020902090209021e-05, | |
| "loss": 1.5448, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.965896589658966e-05, | |
| "loss": 1.5003, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.910891089108911e-05, | |
| "loss": 1.4605, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.8558855885588564e-05, | |
| "loss": 1.4562, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.800880088008801e-05, | |
| "loss": 1.4234, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.745874587458746e-05, | |
| "loss": 1.462, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6887037037037037, | |
| "eval_loss": 1.2266517877578735, | |
| "eval_runtime": 104.4528, | |
| "eval_samples_per_second": 51.698, | |
| "eval_steps_per_second": 3.236, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.690869086908691e-05, | |
| "loss": 1.3493, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.635863586358636e-05, | |
| "loss": 1.2632, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.580858085808581e-05, | |
| "loss": 1.2919, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.525852585258526e-05, | |
| "loss": 1.285, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.470847084708471e-05, | |
| "loss": 1.2564, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.415841584158416e-05, | |
| "loss": 1.2319, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.360836083608361e-05, | |
| "loss": 1.2217, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.305830583058306e-05, | |
| "loss": 1.1776, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.250825082508251e-05, | |
| "loss": 1.2127, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.195819581958196e-05, | |
| "loss": 1.1776, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.140814081408141e-05, | |
| "loss": 1.1651, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.0858085808580864e-05, | |
| "loss": 1.1678, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0308030803080313e-05, | |
| "loss": 1.1173, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9757975797579756e-05, | |
| "loss": 1.1142, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9207920792079208e-05, | |
| "loss": 1.0391, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8657865786578657e-05, | |
| "loss": 1.0514, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.810781078107811e-05, | |
| "loss": 1.0391, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.755775577557756e-05, | |
| "loss": 1.0546, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.700770077007701e-05, | |
| "loss": 1.0664, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.645764576457646e-05, | |
| "loss": 0.9683, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.5907590759075913e-05, | |
| "loss": 0.9964, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.5357535753575355e-05, | |
| "loss": 0.9846, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.480748074807481e-05, | |
| "loss": 0.9348, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.4257425742574257e-05, | |
| "loss": 0.9687, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.370737073707371e-05, | |
| "loss": 0.9263, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.3157315731573158e-05, | |
| "loss": 0.948, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2607260726072607e-05, | |
| "loss": 0.8746, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.2057205720572056e-05, | |
| "loss": 1.0205, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.150715071507151e-05, | |
| "loss": 0.9219, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0957095709570958e-05, | |
| "loss": 0.9119, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0407040704070407e-05, | |
| "loss": 0.9224, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9856985698569856e-05, | |
| "loss": 0.9249, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.930693069306931e-05, | |
| "loss": 0.9007, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.8756875687568758e-05, | |
| "loss": 0.8732, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8009259259259259, | |
| "eval_loss": 0.7092505693435669, | |
| "eval_runtime": 108.4854, | |
| "eval_samples_per_second": 49.776, | |
| "eval_steps_per_second": 3.116, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.8206820682068207e-05, | |
| "loss": 0.9019, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.765676567656766e-05, | |
| "loss": 0.8636, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7106710671067108e-05, | |
| "loss": 0.8994, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6556655665566557e-05, | |
| "loss": 0.8992, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.6006600660066006e-05, | |
| "loss": 0.8894, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.545654565456546e-05, | |
| "loss": 0.904, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.4906490649064908e-05, | |
| "loss": 0.7925, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4356435643564355e-05, | |
| "loss": 0.7882, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3806380638063806e-05, | |
| "loss": 0.9119, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3256325632563257e-05, | |
| "loss": 0.8652, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.2706270627062708e-05, | |
| "loss": 0.8538, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2156215621562157e-05, | |
| "loss": 0.8371, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.1606160616061606e-05, | |
| "loss": 0.8746, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1056105610561057e-05, | |
| "loss": 0.7919, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0506050605060507e-05, | |
| "loss": 0.7718, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.955995599559956e-06, | |
| "loss": 0.8264, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.405940594059407e-06, | |
| "loss": 0.8595, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.855885588558856e-06, | |
| "loss": 0.8308, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.305830583058307e-06, | |
| "loss": 0.8107, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.755775577557756e-06, | |
| "loss": 0.782, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.205720572057206e-06, | |
| "loss": 0.8989, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.655665566556656e-06, | |
| "loss": 0.7427, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 6.105610561056106e-06, | |
| "loss": 0.8377, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.7893, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.005500550055006e-06, | |
| "loss": 0.7916, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.455445544554456e-06, | |
| "loss": 0.7662, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.905390539053906e-06, | |
| "loss": 0.7687, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.3553355335533555e-06, | |
| "loss": 0.8293, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.8052805280528055e-06, | |
| "loss": 0.8026, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.2552255225522554e-06, | |
| "loss": 0.8025, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7051705170517053e-06, | |
| "loss": 0.8072, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.155115511551155e-06, | |
| "loss": 0.8195, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.050605060506051e-07, | |
| "loss": 0.8394, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 5.5005500550055006e-08, | |
| "loss": 0.7706, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8238888888888889, | |
| "eval_loss": 0.6203305125236511, | |
| "eval_runtime": 102.309, | |
| "eval_samples_per_second": 52.781, | |
| "eval_steps_per_second": 3.304, | |
| "step": 1011 | |
| } | |
| ], | |
| "max_steps": 1011, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.374973468635562e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |