| { | |
| "best_metric": 0.9096045197740112, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-eurosat-2/checkpoint-694", | |
| "epoch": 9.974811083123425, | |
| "eval_steps": 500, | |
| "global_step": 990, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 1.2172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 1.0082, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.8736, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.6853, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.7756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.71, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.5979, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.6413, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.5227, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7796610169491526, | |
| "eval_loss": 0.5333397388458252, | |
| "eval_runtime": 5.7182, | |
| "eval_samples_per_second": 30.954, | |
| "eval_steps_per_second": 7.87, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.994388327721661e-05, | |
| "loss": 0.5778, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.5749, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 4.882154882154882e-05, | |
| "loss": 0.4366, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.8260381593714935e-05, | |
| "loss": 0.3629, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.7699214365881036e-05, | |
| "loss": 0.5, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.713804713804714e-05, | |
| "loss": 0.4734, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.6576879910213244e-05, | |
| "loss": 0.4109, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.601571268237935e-05, | |
| "loss": 0.5251, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.3881, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.4893378226711566e-05, | |
| "loss": 0.4248, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_accuracy": 0.8531073446327684, | |
| "eval_loss": 0.4144964814186096, | |
| "eval_runtime": 5.6437, | |
| "eval_samples_per_second": 31.363, | |
| "eval_steps_per_second": 7.974, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.433221099887767e-05, | |
| "loss": 0.3864, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 4.3771043771043774e-05, | |
| "loss": 0.2727, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.3986, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 4.264870931537598e-05, | |
| "loss": 0.2392, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.208754208754209e-05, | |
| "loss": 0.357, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 4.15263748597082e-05, | |
| "loss": 0.2285, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.0965207631874305e-05, | |
| "loss": 0.3227, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.0404040404040405e-05, | |
| "loss": 0.1759, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.984287317620651e-05, | |
| "loss": 0.3358, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 3.9281705948372613e-05, | |
| "loss": 0.2998, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8757062146892656, | |
| "eval_loss": 0.33070680499076843, | |
| "eval_runtime": 5.6516, | |
| "eval_samples_per_second": 31.318, | |
| "eval_steps_per_second": 7.962, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.872053872053872e-05, | |
| "loss": 0.4704, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 3.815937149270483e-05, | |
| "loss": 0.1983, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.7598204264870936e-05, | |
| "loss": 0.188, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2139, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.6475869809203144e-05, | |
| "loss": 0.2216, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 3.5914702581369245e-05, | |
| "loss": 0.2099, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 3.535353535353535e-05, | |
| "loss": 0.278, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 3.4792368125701466e-05, | |
| "loss": 0.226, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 3.423120089786757e-05, | |
| "loss": 0.169, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 3.3670033670033675e-05, | |
| "loss": 0.1704, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8926553672316384, | |
| "eval_loss": 0.26643165946006775, | |
| "eval_runtime": 5.6592, | |
| "eval_samples_per_second": 31.277, | |
| "eval_steps_per_second": 7.952, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.3108866442199775e-05, | |
| "loss": 0.1063, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 3.254769921436588e-05, | |
| "loss": 0.2143, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 3.198653198653199e-05, | |
| "loss": 0.1802, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 3.14253647586981e-05, | |
| "loss": 0.1159, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.1606, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.1828, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.9741863075196406e-05, | |
| "loss": 0.1338, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.9180695847362517e-05, | |
| "loss": 0.208, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.8619528619528618e-05, | |
| "loss": 0.1392, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 2.8058361391694725e-05, | |
| "loss": 0.0684, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8700564971751412, | |
| "eval_loss": 0.4352767765522003, | |
| "eval_runtime": 5.6244, | |
| "eval_samples_per_second": 31.47, | |
| "eval_steps_per_second": 8.001, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 2.7497194163860833e-05, | |
| "loss": 0.1994, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.6936026936026937e-05, | |
| "loss": 0.1901, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.6374859708193044e-05, | |
| "loss": 0.1812, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.581369248035915e-05, | |
| "loss": 0.1002, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 2.5252525252525256e-05, | |
| "loss": 0.0685, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1548, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 2.4130190796857467e-05, | |
| "loss": 0.1409, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 2.356902356902357e-05, | |
| "loss": 0.1636, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 2.3007856341189676e-05, | |
| "loss": 0.1475, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 2.2446689113355783e-05, | |
| "loss": 0.1546, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_accuracy": 0.8870056497175142, | |
| "eval_loss": 0.39201802015304565, | |
| "eval_runtime": 5.5831, | |
| "eval_samples_per_second": 31.703, | |
| "eval_steps_per_second": 8.06, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 2.1885521885521887e-05, | |
| "loss": 0.1232, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 2.132435465768799e-05, | |
| "loss": 0.0651, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.07631874298541e-05, | |
| "loss": 0.0332, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 2.0202020202020203e-05, | |
| "loss": 0.0536, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 1.9640852974186307e-05, | |
| "loss": 0.2526, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 1.9079685746352414e-05, | |
| "loss": 0.218, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0199, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 1.7957351290684622e-05, | |
| "loss": 0.0679, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 1.7396184062850733e-05, | |
| "loss": 0.1341, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.95, | |
| "learning_rate": 1.6835016835016837e-05, | |
| "loss": 0.0593, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.9096045197740112, | |
| "eval_loss": 0.3801310956478119, | |
| "eval_runtime": 5.6406, | |
| "eval_samples_per_second": 31.379, | |
| "eval_steps_per_second": 7.978, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.627384960718294e-05, | |
| "loss": 0.0364, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1.571268237934905e-05, | |
| "loss": 0.0853, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.5151515151515153e-05, | |
| "loss": 0.1463, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.4590347923681259e-05, | |
| "loss": 0.0741, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 1.4029180695847363e-05, | |
| "loss": 0.0982, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 1.3468013468013468e-05, | |
| "loss": 0.0335, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.2906846240179574e-05, | |
| "loss": 0.0494, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0645, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 1.1784511784511786e-05, | |
| "loss": 0.0971, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.1223344556677892e-05, | |
| "loss": 0.0745, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8983050847457628, | |
| "eval_loss": 0.40303125977516174, | |
| "eval_runtime": 5.6355, | |
| "eval_samples_per_second": 31.408, | |
| "eval_steps_per_second": 7.985, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 1.0662177328843996e-05, | |
| "loss": 0.095, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 1.0101010101010101e-05, | |
| "loss": 0.0438, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "learning_rate": 9.539842873176207e-06, | |
| "loss": 0.0136, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 8.978675645342311e-06, | |
| "loss": 0.0702, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 8.417508417508419e-06, | |
| "loss": 0.0943, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 7.856341189674524e-06, | |
| "loss": 0.0746, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 7.295173961840629e-06, | |
| "loss": 0.0562, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 6.734006734006734e-06, | |
| "loss": 0.0372, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.0282, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 5.611672278338946e-06, | |
| "loss": 0.0877, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.903954802259887, | |
| "eval_loss": 0.38457363843917847, | |
| "eval_runtime": 5.5773, | |
| "eval_samples_per_second": 31.736, | |
| "eval_steps_per_second": 8.068, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 5.050505050505051e-06, | |
| "loss": 0.0087, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 4.489337822671156e-06, | |
| "loss": 0.1049, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 3.928170594837262e-06, | |
| "loss": 0.0294, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.367003367003367e-06, | |
| "loss": 0.0892, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.805836139169473e-06, | |
| "loss": 0.1025, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 2.244668911335578e-06, | |
| "loss": 0.1009, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.6835016835016836e-06, | |
| "loss": 0.0784, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 1.122334455667789e-06, | |
| "loss": 0.0662, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.87, | |
| "learning_rate": 5.611672278338944e-07, | |
| "loss": 0.0257, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 0.0, | |
| "loss": 0.09, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_accuracy": 0.903954802259887, | |
| "eval_loss": 0.3815687894821167, | |
| "eval_runtime": 5.5808, | |
| "eval_samples_per_second": 31.716, | |
| "eval_steps_per_second": 8.063, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "step": 990, | |
| "total_flos": 1.252454560310016e+18, | |
| "train_loss": 0.23395052750905354, | |
| "train_runtime": 1693.9771, | |
| "train_samples_per_second": 9.357, | |
| "train_steps_per_second": 0.584 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 990, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.252454560310016e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |