| { | |
| "best_metric": 0.5026926812042023, | |
| "best_model_checkpoint": "vit-base-patch16-224-cl-v1/checkpoint-1059", | |
| "epoch": 2.9978768577494694, | |
| "global_step": 1059, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 6.2828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 6.2963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 6.2779, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 6.2665, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 6.1674, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 6.1256, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 6.0679, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 6.0098, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 5.8964, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 5.8063, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.979013641133264e-05, | |
| "loss": 5.6817, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.926547743966422e-05, | |
| "loss": 5.5657, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.87408184679958e-05, | |
| "loss": 5.4562, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.821615949632739e-05, | |
| "loss": 5.3256, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.769150052465897e-05, | |
| "loss": 5.2464, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.716684155299056e-05, | |
| "loss": 5.139, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.664218258132214e-05, | |
| "loss": 4.9845, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.611752360965373e-05, | |
| "loss": 4.9397, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.5592864637985314e-05, | |
| "loss": 4.7968, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.50682056663169e-05, | |
| "loss": 4.7409, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.454354669464848e-05, | |
| "loss": 4.5975, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.401888772298007e-05, | |
| "loss": 4.498, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.349422875131165e-05, | |
| "loss": 4.4397, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.2969569779643234e-05, | |
| "loss": 4.2942, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.244491080797482e-05, | |
| "loss": 4.3336, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.19202518363064e-05, | |
| "loss": 4.2295, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.139559286463799e-05, | |
| "loss": 4.1694, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.087093389296957e-05, | |
| "loss": 4.1409, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.034627492130116e-05, | |
| "loss": 4.0306, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.982161594963274e-05, | |
| "loss": 4.0209, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.9296956977964325e-05, | |
| "loss": 3.9545, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.877229800629591e-05, | |
| "loss": 3.8019, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.824763903462749e-05, | |
| "loss": 3.8162, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.772298006295908e-05, | |
| "loss": 3.7865, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.719832109129066e-05, | |
| "loss": 3.6762, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.36911803654983666, | |
| "eval_loss": 3.44724440574646, | |
| "eval_runtime": 115.3281, | |
| "eval_samples_per_second": 98.215, | |
| "eval_steps_per_second": 3.07, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.6673662119622245e-05, | |
| "loss": 3.5838, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.614900314795383e-05, | |
| "loss": 3.5665, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5624344176285416e-05, | |
| "loss": 3.5292, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.5099685204617e-05, | |
| "loss": 3.4282, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.457502623294859e-05, | |
| "loss": 3.3845, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.405036726128017e-05, | |
| "loss": 3.3924, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.352570828961175e-05, | |
| "loss": 3.4058, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.3001049317943336e-05, | |
| "loss": 3.3833, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.247639034627492e-05, | |
| "loss": 3.2617, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.195173137460651e-05, | |
| "loss": 3.3425, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.142707240293809e-05, | |
| "loss": 3.3424, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.090241343126968e-05, | |
| "loss": 3.2299, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.037775445960126e-05, | |
| "loss": 3.2087, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.985309548793285e-05, | |
| "loss": 3.3261, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.932843651626443e-05, | |
| "loss": 3.1263, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.8803777544596016e-05, | |
| "loss": 3.1725, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8279118572927598e-05, | |
| "loss": 3.1123, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.775445960125918e-05, | |
| "loss": 3.1397, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.722980062959077e-05, | |
| "loss": 3.0792, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.670514165792235e-05, | |
| "loss": 3.1139, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.618048268625394e-05, | |
| "loss": 3.0661, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.565582371458552e-05, | |
| "loss": 2.9836, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.5131164742917107e-05, | |
| "loss": 3.0594, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.460650577124869e-05, | |
| "loss": 3.0009, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4081846799580274e-05, | |
| "loss": 2.9742, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.355718782791186e-05, | |
| "loss": 2.9865, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.3032528856243445e-05, | |
| "loss": 2.9613, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2507869884575027e-05, | |
| "loss": 2.8343, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.1983210912906612e-05, | |
| "loss": 2.8331, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.1458551941238197e-05, | |
| "loss": 2.841, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.093389296956978e-05, | |
| "loss": 2.9325, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0409233997901365e-05, | |
| "loss": 2.8804, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.988457502623295e-05, | |
| "loss": 2.8735, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9359916054564532e-05, | |
| "loss": 2.7896, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.8835257082896118e-05, | |
| "loss": 2.8516, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4738236073099673, | |
| "eval_loss": 2.5892348289489746, | |
| "eval_runtime": 115.2002, | |
| "eval_samples_per_second": 98.324, | |
| "eval_steps_per_second": 3.073, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.8310598111227703e-05, | |
| "loss": 2.7745, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.7785939139559288e-05, | |
| "loss": 2.7601, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.7261280167890874e-05, | |
| "loss": 2.698, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.6736621196222456e-05, | |
| "loss": 2.7889, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.621196222455404e-05, | |
| "loss": 2.659, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.5687303252885623e-05, | |
| "loss": 2.7226, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.5162644281217208e-05, | |
| "loss": 2.6826, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4637985309548794e-05, | |
| "loss": 2.7309, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4113326337880377e-05, | |
| "loss": 2.7316, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3588667366211963e-05, | |
| "loss": 2.6837, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3064008394543548e-05, | |
| "loss": 2.6828, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.2539349422875132e-05, | |
| "loss": 2.7098, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2014690451206716e-05, | |
| "loss": 2.7163, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1490031479538301e-05, | |
| "loss": 2.662, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.0965372507869885e-05, | |
| "loss": 2.7605, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.044071353620147e-05, | |
| "loss": 2.733, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.916054564533055e-06, | |
| "loss": 2.6798, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 9.391395592864637e-06, | |
| "loss": 2.6339, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.866736621196223e-06, | |
| "loss": 2.5773, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.342077649527808e-06, | |
| "loss": 2.6628, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 7.817418677859392e-06, | |
| "loss": 2.6797, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.2927597061909755e-06, | |
| "loss": 2.6, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.76810073452256e-06, | |
| "loss": 2.6314, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.243441762854145e-06, | |
| "loss": 2.616, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.71878279118573e-06, | |
| "loss": 2.5554, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 5.194123819517314e-06, | |
| "loss": 2.6585, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.669464847848898e-06, | |
| "loss": 2.5669, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 4.144805876180483e-06, | |
| "loss": 2.5999, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.620146904512067e-06, | |
| "loss": 2.5379, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.0954879328436517e-06, | |
| "loss": 2.7058, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.5708289611752362e-06, | |
| "loss": 2.6027, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.0461699895068208e-06, | |
| "loss": 2.6097, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.521511017838405e-06, | |
| "loss": 2.5863, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.968520461699896e-07, | |
| "loss": 2.5802, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.7219307450157403e-07, | |
| "loss": 2.6887, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5026926812042023, | |
| "eval_loss": 2.4053452014923096, | |
| "eval_runtime": 115.1212, | |
| "eval_samples_per_second": 98.392, | |
| "eval_steps_per_second": 3.075, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1059, | |
| "total_flos": 1.0544682063529378e+19, | |
| "train_loss": 3.5929441298934175, | |
| "train_runtime": 3262.3183, | |
| "train_samples_per_second": 41.554, | |
| "train_steps_per_second": 0.325 | |
| } | |
| ], | |
| "max_steps": 1059, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.0544682063529378e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |