| { | |
| "best_metric": 0.787, | |
| "best_model_checkpoint": "mobilevit-small-finetuned/checkpoint-1053", | |
| "epoch": 2.9936034115138592, | |
| "global_step": 1053, | |
| "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": 2.3133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 2.3071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 2.3019, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 2.2977, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 2.2882, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 2.2742, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 2.2587, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 2.2425, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 2.2217, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 2.1898, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.978880675818374e-05, | |
| "loss": 2.1479, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.9260823653643085e-05, | |
| "loss": 2.1012, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.8732840549102435e-05, | |
| "loss": 2.0467, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.820485744456177e-05, | |
| "loss": 2.0014, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.767687434002112e-05, | |
| "loss": 1.9434, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.7148891235480466e-05, | |
| "loss": 1.8817, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.662090813093981e-05, | |
| "loss": 1.8359, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.609292502639916e-05, | |
| "loss": 1.8028, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.55649419218585e-05, | |
| "loss": 1.7679, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.503695881731785e-05, | |
| "loss": 1.7312, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.45089757127772e-05, | |
| "loss": 1.6759, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.398099260823654e-05, | |
| "loss": 1.6758, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3453009503695884e-05, | |
| "loss": 1.659, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.292502639915523e-05, | |
| "loss": 1.6032, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.239704329461457e-05, | |
| "loss": 1.5838, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.186906019007392e-05, | |
| "loss": 1.5343, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.1341077085533265e-05, | |
| "loss": 1.5382, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.081309398099261e-05, | |
| "loss": 1.4849, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.028511087645195e-05, | |
| "loss": 1.4647, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.97571277719113e-05, | |
| "loss": 1.4585, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.9229144667370646e-05, | |
| "loss": 1.4659, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.870116156282999e-05, | |
| "loss": 1.4198, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.817317845828934e-05, | |
| "loss": 1.3863, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.764519535374868e-05, | |
| "loss": 1.3862, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.711721224920803e-05, | |
| "loss": 1.357, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6832, | |
| "eval_loss": 1.077993631362915, | |
| "eval_runtime": 32.5464, | |
| "eval_samples_per_second": 153.627, | |
| "eval_steps_per_second": 4.824, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.658922914466738e-05, | |
| "loss": 1.3951, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6061246040126714e-05, | |
| "loss": 1.3388, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5533262935586064e-05, | |
| "loss": 1.3443, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.500527983104541e-05, | |
| "loss": 1.3312, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.447729672650475e-05, | |
| "loss": 1.3284, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.3949313621964095e-05, | |
| "loss": 1.2881, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.3421330517423445e-05, | |
| "loss": 1.2698, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.289334741288279e-05, | |
| "loss": 1.2669, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.236536430834213e-05, | |
| "loss": 1.2858, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.183738120380148e-05, | |
| "loss": 1.2497, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.130939809926082e-05, | |
| "loss": 1.2442, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.078141499472017e-05, | |
| "loss": 1.2177, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.0253431890179517e-05, | |
| "loss": 1.2528, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.972544878563886e-05, | |
| "loss": 1.2149, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9197465681098207e-05, | |
| "loss": 1.1902, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8669482576557548e-05, | |
| "loss": 1.219, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8141499472016898e-05, | |
| "loss": 1.1731, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7613516367476245e-05, | |
| "loss": 1.173, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7085533262935585e-05, | |
| "loss": 1.2019, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.6557550158394935e-05, | |
| "loss": 1.1499, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.6029567053854276e-05, | |
| "loss": 1.1832, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5501583949313622e-05, | |
| "loss": 1.1644, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.497360084477297e-05, | |
| "loss": 1.1277, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.4445617740232313e-05, | |
| "loss": 1.1444, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.391763463569166e-05, | |
| "loss": 1.1338, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.3389651531151003e-05, | |
| "loss": 1.1282, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.286166842661035e-05, | |
| "loss": 1.1405, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.2333685322069694e-05, | |
| "loss": 1.1354, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.180570221752904e-05, | |
| "loss": 1.0918, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.1277719112988384e-05, | |
| "loss": 1.1221, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.074973600844773e-05, | |
| "loss": 1.1571, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0221752903907075e-05, | |
| "loss": 1.0985, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9693769799366422e-05, | |
| "loss": 1.0932, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.9165786694825765e-05, | |
| "loss": 1.0909, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.863780359028511e-05, | |
| "loss": 1.068, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7722, | |
| "eval_loss": 0.7430154085159302, | |
| "eval_runtime": 32.8722, | |
| "eval_samples_per_second": 152.104, | |
| "eval_steps_per_second": 4.776, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.810982048574446e-05, | |
| "loss": 1.0776, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7581837381203803e-05, | |
| "loss": 1.1051, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.7053854276663146e-05, | |
| "loss": 1.0272, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.6525871172122493e-05, | |
| "loss": 1.0538, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.5997888067581837e-05, | |
| "loss": 1.0412, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5469904963041184e-05, | |
| "loss": 1.0662, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.4941921858500529e-05, | |
| "loss": 1.0629, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4413938753959874e-05, | |
| "loss": 1.0141, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.388595564941922e-05, | |
| "loss": 1.0644, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.3357972544878563e-05, | |
| "loss": 1.076, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2829989440337912e-05, | |
| "loss": 1.0706, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2302006335797255e-05, | |
| "loss": 1.0861, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.17740232312566e-05, | |
| "loss": 1.0797, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1246040126715946e-05, | |
| "loss": 1.025, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0718057022175291e-05, | |
| "loss": 1.0459, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0190073917634636e-05, | |
| "loss": 1.0512, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 9.662090813093982e-06, | |
| "loss": 0.9911, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.134107708553327e-06, | |
| "loss": 1.0766, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 8.606124604012672e-06, | |
| "loss": 1.0432, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.078141499472017e-06, | |
| "loss": 1.0811, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 7.5501583949313625e-06, | |
| "loss": 1.0485, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 7.022175290390708e-06, | |
| "loss": 1.027, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 6.494192185850054e-06, | |
| "loss": 1.0089, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.966209081309398e-06, | |
| "loss": 1.0524, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.438225976768744e-06, | |
| "loss": 1.0755, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.910242872228089e-06, | |
| "loss": 1.0055, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 4.382259767687434e-06, | |
| "loss": 1.0355, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.854276663146779e-06, | |
| "loss": 1.0914, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 3.326293558606125e-06, | |
| "loss": 1.0311, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.79831045406547e-06, | |
| "loss": 1.0628, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.2703273495248154e-06, | |
| "loss": 1.0107, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.7423442449841606e-06, | |
| "loss": 0.9532, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.2143611404435059e-06, | |
| "loss": 0.9952, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 6.863780359028511e-07, | |
| "loss": 1.0368, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.5839493136219642e-07, | |
| "loss": 1.0103, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.787, | |
| "eval_loss": 0.6787326335906982, | |
| "eval_runtime": 32.1464, | |
| "eval_samples_per_second": 155.538, | |
| "eval_steps_per_second": 4.884, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1053, | |
| "total_flos": 9.945423521440727e+17, | |
| "train_loss": 1.3631520318849135, | |
| "train_runtime": 2301.7838, | |
| "train_samples_per_second": 58.65, | |
| "train_steps_per_second": 0.457 | |
| } | |
| ], | |
| "max_steps": 1053, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.945423521440727e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |