| { | |
| "best_metric": 0.9975461431772111, | |
| "best_model_checkpoint": "PlantDiseaseDetectorSwinv2/checkpoint-879", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 879, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.034129692832764506, | |
| "grad_norm": 2.5705349445343018, | |
| "learning_rate": 5.681818181818182e-06, | |
| "loss": 3.8022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06825938566552901, | |
| "grad_norm": 2.408888816833496, | |
| "learning_rate": 1.1363636363636365e-05, | |
| "loss": 3.7314, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10238907849829351, | |
| "grad_norm": 3.7745347023010254, | |
| "learning_rate": 1.7045454545454546e-05, | |
| "loss": 3.5832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13651877133105803, | |
| "grad_norm": 5.221632480621338, | |
| "learning_rate": 2.272727272727273e-05, | |
| "loss": 3.279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17064846416382254, | |
| "grad_norm": 5.78312873840332, | |
| "learning_rate": 2.8409090909090912e-05, | |
| "loss": 2.6879, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20477815699658702, | |
| "grad_norm": 6.596199989318848, | |
| "learning_rate": 3.409090909090909e-05, | |
| "loss": 1.8838, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23890784982935154, | |
| "grad_norm": 6.6335601806640625, | |
| "learning_rate": 3.9772727272727275e-05, | |
| "loss": 1.2296, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.27303754266211605, | |
| "grad_norm": 5.116641044616699, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 0.7926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.30716723549488056, | |
| "grad_norm": 5.051211833953857, | |
| "learning_rate": 4.9873577749683945e-05, | |
| "loss": 0.5453, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3412969283276451, | |
| "grad_norm": 5.704665660858154, | |
| "learning_rate": 4.924146649810367e-05, | |
| "loss": 0.427, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37542662116040953, | |
| "grad_norm": 4.636778354644775, | |
| "learning_rate": 4.860935524652339e-05, | |
| "loss": 0.3498, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.40955631399317405, | |
| "grad_norm": 4.307668209075928, | |
| "learning_rate": 4.797724399494311e-05, | |
| "loss": 0.2841, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.44368600682593856, | |
| "grad_norm": 3.284649610519409, | |
| "learning_rate": 4.734513274336283e-05, | |
| "loss": 0.2521, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4778156996587031, | |
| "grad_norm": 3.6471190452575684, | |
| "learning_rate": 4.6713021491782554e-05, | |
| "loss": 0.2052, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5119453924914675, | |
| "grad_norm": 3.599177837371826, | |
| "learning_rate": 4.608091024020228e-05, | |
| "loss": 0.2033, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5460750853242321, | |
| "grad_norm": 3.1162948608398438, | |
| "learning_rate": 4.5448798988622e-05, | |
| "loss": 0.1772, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5802047781569966, | |
| "grad_norm": 3.1850969791412354, | |
| "learning_rate": 4.4816687737041726e-05, | |
| "loss": 0.1589, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6143344709897611, | |
| "grad_norm": 3.5049831867218018, | |
| "learning_rate": 4.418457648546144e-05, | |
| "loss": 0.147, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6484641638225256, | |
| "grad_norm": 3.1032307147979736, | |
| "learning_rate": 4.355246523388117e-05, | |
| "loss": 0.158, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6825938566552902, | |
| "grad_norm": 4.088365077972412, | |
| "learning_rate": 4.2920353982300885e-05, | |
| "loss": 0.1373, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7167235494880546, | |
| "grad_norm": 3.2553369998931885, | |
| "learning_rate": 4.2288242730720607e-05, | |
| "loss": 0.137, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7508532423208191, | |
| "grad_norm": 3.4594857692718506, | |
| "learning_rate": 4.165613147914033e-05, | |
| "loss": 0.1241, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7849829351535836, | |
| "grad_norm": 3.20019793510437, | |
| "learning_rate": 4.102402022756005e-05, | |
| "loss": 0.1049, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8191126279863481, | |
| "grad_norm": 2.817979335784912, | |
| "learning_rate": 4.039190897597978e-05, | |
| "loss": 0.1055, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8532423208191127, | |
| "grad_norm": 2.961674451828003, | |
| "learning_rate": 3.9759797724399494e-05, | |
| "loss": 0.1116, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8873720136518771, | |
| "grad_norm": 1.5384647846221924, | |
| "learning_rate": 3.912768647281922e-05, | |
| "loss": 0.1147, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9215017064846417, | |
| "grad_norm": 2.3770840167999268, | |
| "learning_rate": 3.849557522123894e-05, | |
| "loss": 0.0816, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9556313993174061, | |
| "grad_norm": 1.9292172193527222, | |
| "learning_rate": 3.7863463969658666e-05, | |
| "loss": 0.1042, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9897610921501706, | |
| "grad_norm": 1.9912846088409424, | |
| "learning_rate": 3.723135271807838e-05, | |
| "loss": 0.082, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.989971193854689, | |
| "eval_loss": 0.030839812010526657, | |
| "eval_runtime": 85.4261, | |
| "eval_samples_per_second": 109.721, | |
| "eval_steps_per_second": 1.721, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.023890784982935, | |
| "grad_norm": 2.500840902328491, | |
| "learning_rate": 3.659924146649811e-05, | |
| "loss": 0.0819, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0580204778156996, | |
| "grad_norm": 2.5703957080841064, | |
| "learning_rate": 3.5967130214917824e-05, | |
| "loss": 0.0824, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.0921501706484642, | |
| "grad_norm": 2.538381338119507, | |
| "learning_rate": 3.533501896333755e-05, | |
| "loss": 0.0781, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.1262798634812285, | |
| "grad_norm": 2.861043691635132, | |
| "learning_rate": 3.470290771175727e-05, | |
| "loss": 0.088, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.1604095563139931, | |
| "grad_norm": 1.385380744934082, | |
| "learning_rate": 3.407079646017699e-05, | |
| "loss": 0.0597, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.1945392491467577, | |
| "grad_norm": 2.4261908531188965, | |
| "learning_rate": 3.343868520859672e-05, | |
| "loss": 0.0553, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2286689419795223, | |
| "grad_norm": 2.731848955154419, | |
| "learning_rate": 3.280657395701643e-05, | |
| "loss": 0.0626, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.2627986348122868, | |
| "grad_norm": 2.3727986812591553, | |
| "learning_rate": 3.217446270543616e-05, | |
| "loss": 0.0557, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.2969283276450512, | |
| "grad_norm": 2.083387851715088, | |
| "learning_rate": 3.1542351453855877e-05, | |
| "loss": 0.0613, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.3310580204778157, | |
| "grad_norm": 2.408942699432373, | |
| "learning_rate": 3.0910240202275605e-05, | |
| "loss": 0.0563, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.36518771331058, | |
| "grad_norm": 3.069532632827759, | |
| "learning_rate": 3.0278128950695323e-05, | |
| "loss": 0.0562, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3993174061433447, | |
| "grad_norm": 1.5006905794143677, | |
| "learning_rate": 2.964601769911505e-05, | |
| "loss": 0.058, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.4334470989761092, | |
| "grad_norm": 1.9760173559188843, | |
| "learning_rate": 2.9013906447534767e-05, | |
| "loss": 0.0506, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.4675767918088738, | |
| "grad_norm": 1.7346736192703247, | |
| "learning_rate": 2.8381795195954492e-05, | |
| "loss": 0.0583, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.5017064846416384, | |
| "grad_norm": 1.4648014307022095, | |
| "learning_rate": 2.774968394437421e-05, | |
| "loss": 0.0543, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.5358361774744027, | |
| "grad_norm": 0.9175078272819519, | |
| "learning_rate": 2.7117572692793936e-05, | |
| "loss": 0.0524, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.5699658703071673, | |
| "grad_norm": 2.2401745319366455, | |
| "learning_rate": 2.6485461441213654e-05, | |
| "loss": 0.0509, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.6040955631399316, | |
| "grad_norm": 1.0729519128799438, | |
| "learning_rate": 2.5853350189633372e-05, | |
| "loss": 0.0465, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.6382252559726962, | |
| "grad_norm": 1.1426705121994019, | |
| "learning_rate": 2.5221238938053098e-05, | |
| "loss": 0.0492, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.6723549488054608, | |
| "grad_norm": 2.0277466773986816, | |
| "learning_rate": 2.458912768647282e-05, | |
| "loss": 0.0408, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.7064846416382253, | |
| "grad_norm": 1.5704808235168457, | |
| "learning_rate": 2.3957016434892544e-05, | |
| "loss": 0.0504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.74061433447099, | |
| "grad_norm": 1.7388916015625, | |
| "learning_rate": 2.3324905183312266e-05, | |
| "loss": 0.0516, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.7747440273037542, | |
| "grad_norm": 1.4998822212219238, | |
| "learning_rate": 2.2692793931731988e-05, | |
| "loss": 0.038, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.8088737201365188, | |
| "grad_norm": 1.8269169330596924, | |
| "learning_rate": 2.206068268015171e-05, | |
| "loss": 0.0419, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.8430034129692832, | |
| "grad_norm": 1.9325296878814697, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.0422, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.8771331058020477, | |
| "grad_norm": 2.244913101196289, | |
| "learning_rate": 2.079646017699115e-05, | |
| "loss": 0.0464, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.9112627986348123, | |
| "grad_norm": 1.4655271768569946, | |
| "learning_rate": 2.016434892541087e-05, | |
| "loss": 0.035, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.9453924914675769, | |
| "grad_norm": 1.888059377670288, | |
| "learning_rate": 1.9532237673830593e-05, | |
| "loss": 0.0479, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.9795221843003414, | |
| "grad_norm": 2.545102596282959, | |
| "learning_rate": 1.8900126422250315e-05, | |
| "loss": 0.0427, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9955190440627334, | |
| "eval_loss": 0.011397087946534157, | |
| "eval_runtime": 82.3517, | |
| "eval_samples_per_second": 113.817, | |
| "eval_steps_per_second": 1.785, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 2.013651877133106, | |
| "grad_norm": 1.9391770362854004, | |
| "learning_rate": 1.8268015170670037e-05, | |
| "loss": 0.0418, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.04778156996587, | |
| "grad_norm": 1.7138864994049072, | |
| "learning_rate": 1.7635903919089762e-05, | |
| "loss": 0.0354, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0819112627986347, | |
| "grad_norm": 1.8861690759658813, | |
| "learning_rate": 1.7003792667509484e-05, | |
| "loss": 0.035, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.1160409556313993, | |
| "grad_norm": 0.7711435556411743, | |
| "learning_rate": 1.6371681415929206e-05, | |
| "loss": 0.0304, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.150170648464164, | |
| "grad_norm": 1.925860047340393, | |
| "learning_rate": 1.5739570164348927e-05, | |
| "loss": 0.0319, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.1843003412969284, | |
| "grad_norm": 1.1292275190353394, | |
| "learning_rate": 1.510745891276865e-05, | |
| "loss": 0.0319, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.218430034129693, | |
| "grad_norm": 1.2774521112442017, | |
| "learning_rate": 1.4475347661188371e-05, | |
| "loss": 0.0301, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.252559726962457, | |
| "grad_norm": 3.394732713699341, | |
| "learning_rate": 1.3843236409608093e-05, | |
| "loss": 0.034, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.2866894197952217, | |
| "grad_norm": 0.9372479319572449, | |
| "learning_rate": 1.3211125158027813e-05, | |
| "loss": 0.0345, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.3208191126279862, | |
| "grad_norm": 1.1731668710708618, | |
| "learning_rate": 1.2579013906447535e-05, | |
| "loss": 0.0305, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.354948805460751, | |
| "grad_norm": 1.8510732650756836, | |
| "learning_rate": 1.1946902654867258e-05, | |
| "loss": 0.0246, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.3890784982935154, | |
| "grad_norm": 1.2375292778015137, | |
| "learning_rate": 1.1314791403286978e-05, | |
| "loss": 0.0276, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.42320819112628, | |
| "grad_norm": 1.7051323652267456, | |
| "learning_rate": 1.06826801517067e-05, | |
| "loss": 0.0343, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.4573378839590445, | |
| "grad_norm": 1.9090622663497925, | |
| "learning_rate": 1.0050568900126423e-05, | |
| "loss": 0.0295, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.491467576791809, | |
| "grad_norm": 2.412919759750366, | |
| "learning_rate": 9.418457648546145e-06, | |
| "loss": 0.0261, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.5255972696245736, | |
| "grad_norm": 1.2371612787246704, | |
| "learning_rate": 8.786346396965867e-06, | |
| "loss": 0.0264, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.5597269624573378, | |
| "grad_norm": 1.0463935136795044, | |
| "learning_rate": 8.154235145385589e-06, | |
| "loss": 0.021, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.5938566552901023, | |
| "grad_norm": 0.7903943061828613, | |
| "learning_rate": 7.52212389380531e-06, | |
| "loss": 0.0245, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.627986348122867, | |
| "grad_norm": 0.9663693308830261, | |
| "learning_rate": 6.890012642225031e-06, | |
| "loss": 0.0247, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.6621160409556315, | |
| "grad_norm": 0.8555452227592468, | |
| "learning_rate": 6.257901390644753e-06, | |
| "loss": 0.0219, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.696245733788396, | |
| "grad_norm": 2.052835702896118, | |
| "learning_rate": 5.625790139064476e-06, | |
| "loss": 0.0294, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.73037542662116, | |
| "grad_norm": 3.152604579925537, | |
| "learning_rate": 4.993678887484197e-06, | |
| "loss": 0.03, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.7645051194539247, | |
| "grad_norm": 1.7257556915283203, | |
| "learning_rate": 4.361567635903919e-06, | |
| "loss": 0.0278, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.7986348122866893, | |
| "grad_norm": 1.7202658653259277, | |
| "learning_rate": 3.729456384323641e-06, | |
| "loss": 0.0274, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.832764505119454, | |
| "grad_norm": 1.6560910940170288, | |
| "learning_rate": 3.097345132743363e-06, | |
| "loss": 0.0297, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.8668941979522184, | |
| "grad_norm": 2.1152303218841553, | |
| "learning_rate": 2.465233881163085e-06, | |
| "loss": 0.0254, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.901023890784983, | |
| "grad_norm": 1.8419415950775146, | |
| "learning_rate": 1.8331226295828066e-06, | |
| "loss": 0.0257, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.9351535836177476, | |
| "grad_norm": 1.0680209398269653, | |
| "learning_rate": 1.2010113780025286e-06, | |
| "loss": 0.024, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.969283276450512, | |
| "grad_norm": 2.186582565307617, | |
| "learning_rate": 5.689001264222504e-07, | |
| "loss": 0.0341, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9975461431772111, | |
| "eval_loss": 0.007486232556402683, | |
| "eval_runtime": 82.1973, | |
| "eval_samples_per_second": 114.031, | |
| "eval_steps_per_second": 1.788, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 879, | |
| "total_flos": 7.327526150669599e+18, | |
| "train_loss": 0.31240319909021447, | |
| "train_runtime": 6548.0515, | |
| "train_samples_per_second": 34.355, | |
| "train_steps_per_second": 0.134 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 879, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.327526150669599e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |