layout-xlm-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512
/
checkpoint-6400
/trainer_state.json
| { | |
| "best_metric": 0.7893899204244033, | |
| "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_paragraphs_ml512-v6/checkpoint-6400", | |
| "epoch": 3.411513859275053, | |
| "global_step": 6400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.8841533429944805, | |
| "eval_f1": 0.10664094791953704, | |
| "eval_loss": 0.4427741765975952, | |
| "eval_precision": 0.11536168521462639, | |
| "eval_recall": 0.09914602903501281, | |
| "eval_runtime": 348.7843, | |
| "eval_samples_per_second": 4.607, | |
| "eval_steps_per_second": 0.29, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.9242655812394248, | |
| "eval_f1": 0.44395873404441333, | |
| "eval_loss": 0.30403900146484375, | |
| "eval_precision": 0.4547734193086154, | |
| "eval_recall": 0.4336464560204953, | |
| "eval_runtime": 350.1211, | |
| "eval_samples_per_second": 4.59, | |
| "eval_steps_per_second": 0.288, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.3209054593874834e-05, | |
| "loss": 0.7241, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.9359434268564053, | |
| "eval_f1": 0.5543897040741045, | |
| "eval_loss": 0.22647875547409058, | |
| "eval_precision": 0.5330233291298865, | |
| "eval_recall": 0.5775405636208369, | |
| "eval_runtime": 342.3688, | |
| "eval_samples_per_second": 4.694, | |
| "eval_steps_per_second": 0.295, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.947861481323102, | |
| "eval_f1": 0.6015281512784394, | |
| "eval_loss": 0.2140066921710968, | |
| "eval_precision": 0.6013484680378937, | |
| "eval_recall": 0.6017079419299743, | |
| "eval_runtime": 342.7133, | |
| "eval_samples_per_second": 4.689, | |
| "eval_steps_per_second": 0.295, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.927439656448986e-05, | |
| "loss": 0.2343, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.9402091136821377, | |
| "eval_f1": 0.6132131856006622, | |
| "eval_loss": 0.285193532705307, | |
| "eval_precision": 0.6641768748132656, | |
| "eval_recall": 0.5695132365499573, | |
| "eval_runtime": 341.4863, | |
| "eval_samples_per_second": 4.706, | |
| "eval_steps_per_second": 0.296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.9539986854504707, | |
| "eval_f1": 0.6604133950171894, | |
| "eval_loss": 0.16944007575511932, | |
| "eval_precision": 0.6564846848367226, | |
| "eval_recall": 0.6643894107600341, | |
| "eval_runtime": 342.4627, | |
| "eval_samples_per_second": 4.692, | |
| "eval_steps_per_second": 0.295, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.9354234142916347, | |
| "eval_f1": 0.6198065842234727, | |
| "eval_loss": 0.230770543217659, | |
| "eval_precision": 0.5118828964212166, | |
| "eval_recall": 0.785397096498719, | |
| "eval_runtime": 332.1227, | |
| "eval_samples_per_second": 4.839, | |
| "eval_steps_per_second": 0.304, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.7793573226714055e-05, | |
| "loss": 0.1913, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.9593994250825553, | |
| "eval_f1": 0.6589563286454478, | |
| "eval_loss": 0.1601293832063675, | |
| "eval_precision": 0.7189582071471835, | |
| "eval_recall": 0.6081981212638771, | |
| "eval_runtime": 327.08, | |
| "eval_samples_per_second": 4.913, | |
| "eval_steps_per_second": 0.309, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.9540725958657681, | |
| "eval_f1": 0.6596589238459277, | |
| "eval_loss": 0.16707618534564972, | |
| "eval_precision": 0.5790424570912376, | |
| "eval_recall": 0.7663535439795047, | |
| "eval_runtime": 324.9043, | |
| "eval_samples_per_second": 4.946, | |
| "eval_steps_per_second": 0.311, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.6315711535613804e-05, | |
| "loss": 0.1346, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_accuracy": 0.9611943923112051, | |
| "eval_f1": 0.6985545993817363, | |
| "eval_loss": 0.15802155435085297, | |
| "eval_precision": 0.6837585868498528, | |
| "eval_recall": 0.71400512382579, | |
| "eval_runtime": 326.3436, | |
| "eval_samples_per_second": 4.924, | |
| "eval_steps_per_second": 0.309, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.9597082650321906, | |
| "eval_f1": 0.6896523517382412, | |
| "eval_loss": 0.14230071008205414, | |
| "eval_precision": 0.661773940345369, | |
| "eval_recall": 0.7199829205807002, | |
| "eval_runtime": 352.3832, | |
| "eval_samples_per_second": 4.56, | |
| "eval_steps_per_second": 0.287, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.9662862919936542, | |
| "eval_f1": 0.6980116745713244, | |
| "eval_loss": 0.15801101922988892, | |
| "eval_precision": 0.7489724016441573, | |
| "eval_recall": 0.6535439795046969, | |
| "eval_runtime": 346.3949, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 0.292, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.483784984451355e-05, | |
| "loss": 0.098, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.9615850616492053, | |
| "eval_f1": 0.6800371073905552, | |
| "eval_loss": 0.1394117921590805, | |
| "eval_precision": 0.7044019401482566, | |
| "eval_recall": 0.6573014517506405, | |
| "eval_runtime": 340.6651, | |
| "eval_samples_per_second": 4.717, | |
| "eval_steps_per_second": 0.296, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_accuracy": 0.9685537579486693, | |
| "eval_f1": 0.725116373203805, | |
| "eval_loss": 0.1756211668252945, | |
| "eval_precision": 0.6892651019622932, | |
| "eval_recall": 0.7649017933390265, | |
| "eval_runtime": 336.4339, | |
| "eval_samples_per_second": 4.777, | |
| "eval_steps_per_second": 0.3, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.33599881534133e-05, | |
| "loss": 0.0999, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.9636387153313958, | |
| "eval_f1": 0.69845832244578, | |
| "eval_loss": 0.154231458902359, | |
| "eval_precision": 0.7126733025239957, | |
| "eval_recall": 0.684799316823228, | |
| "eval_runtime": 338.3198, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 0.299, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_accuracy": 0.9670465134081412, | |
| "eval_f1": 0.7096949152542371, | |
| "eval_loss": 0.11871206015348434, | |
| "eval_precision": 0.7538166106577052, | |
| "eval_recall": 0.6704526046114432, | |
| "eval_runtime": 330.1098, | |
| "eval_samples_per_second": 4.868, | |
| "eval_steps_per_second": 0.306, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_accuracy": 0.9585151397566763, | |
| "eval_f1": 0.7426724326213252, | |
| "eval_loss": 0.17930778861045837, | |
| "eval_precision": 0.7601716891710633, | |
| "eval_recall": 0.7259607173356106, | |
| "eval_runtime": 334.0583, | |
| "eval_samples_per_second": 4.811, | |
| "eval_steps_per_second": 0.302, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.1879164815637496e-05, | |
| "loss": 0.0972, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.9621024345562867, | |
| "eval_f1": 0.7188762229602368, | |
| "eval_loss": 0.18358349800109863, | |
| "eval_precision": 0.7575671585319712, | |
| "eval_recall": 0.6839453458582408, | |
| "eval_runtime": 323.7426, | |
| "eval_samples_per_second": 4.964, | |
| "eval_steps_per_second": 0.312, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.9641745658423015, | |
| "eval_f1": 0.7188527825286147, | |
| "eval_loss": 0.1464972347021103, | |
| "eval_precision": 0.7388443162354638, | |
| "eval_recall": 0.6999146029035013, | |
| "eval_runtime": 324.6992, | |
| "eval_samples_per_second": 4.949, | |
| "eval_steps_per_second": 0.311, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.0398341477861691e-05, | |
| "loss": 0.0662, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.9690632118826831, | |
| "eval_f1": 0.7450159228722244, | |
| "eval_loss": 0.1409263014793396, | |
| "eval_precision": 0.7615267992508695, | |
| "eval_recall": 0.7292058070025619, | |
| "eval_runtime": 314.9474, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 0.321, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.9615428271261782, | |
| "eval_f1": 0.7431866723622383, | |
| "eval_loss": 0.17204762995243073, | |
| "eval_precision": 0.7435042735042735, | |
| "eval_recall": 0.7428693424423569, | |
| "eval_runtime": 307.7666, | |
| "eval_samples_per_second": 5.221, | |
| "eval_steps_per_second": 0.328, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_accuracy": 0.9666637630432086, | |
| "eval_f1": 0.7338054481470216, | |
| "eval_loss": 0.14404301345348358, | |
| "eval_precision": 0.7468824621915627, | |
| "eval_recall": 0.7211784799316823, | |
| "eval_runtime": 310.6556, | |
| "eval_samples_per_second": 5.173, | |
| "eval_steps_per_second": 0.325, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 8.917518140085888e-06, | |
| "loss": 0.0581, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_accuracy": 0.9657451621673702, | |
| "eval_f1": 0.7135284422468708, | |
| "eval_loss": 0.19275733828544617, | |
| "eval_precision": 0.7457863860694665, | |
| "eval_recall": 0.6839453458582408, | |
| "eval_runtime": 303.8599, | |
| "eval_samples_per_second": 5.289, | |
| "eval_steps_per_second": 0.332, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.969187275794075, | |
| "eval_f1": 0.7378380713730234, | |
| "eval_loss": 0.16446392238140106, | |
| "eval_precision": 0.7466771598461001, | |
| "eval_recall": 0.7292058070025619, | |
| "eval_runtime": 304.6717, | |
| "eval_samples_per_second": 5.275, | |
| "eval_steps_per_second": 0.332, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 7.436694802310085e-06, | |
| "loss": 0.0538, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_accuracy": 0.9655762240752619, | |
| "eval_f1": 0.7619294158253516, | |
| "eval_loss": 0.15173019468784332, | |
| "eval_precision": 0.7699686083013603, | |
| "eval_recall": 0.7540563620836892, | |
| "eval_runtime": 301.8453, | |
| "eval_samples_per_second": 5.324, | |
| "eval_steps_per_second": 0.335, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "eval_accuracy": 0.9683900991719394, | |
| "eval_f1": 0.7727910873601738, | |
| "eval_loss": 0.16763265430927277, | |
| "eval_precision": 0.8226786230835985, | |
| "eval_recall": 0.7286080273270709, | |
| "eval_runtime": 303.0486, | |
| "eval_samples_per_second": 5.303, | |
| "eval_steps_per_second": 0.333, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.9724974065363203, | |
| "eval_f1": 0.7607919220424181, | |
| "eval_loss": 0.12770096957683563, | |
| "eval_precision": 0.7864891968274227, | |
| "eval_recall": 0.7367207514944492, | |
| "eval_runtime": 298.6206, | |
| "eval_samples_per_second": 5.381, | |
| "eval_steps_per_second": 0.338, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 5.955871464534282e-06, | |
| "loss": 0.0432, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.9692585465516832, | |
| "eval_f1": 0.7784317119612255, | |
| "eval_loss": 0.15319885313510895, | |
| "eval_precision": 0.78908580452711, | |
| "eval_recall": 0.7680614859094791, | |
| "eval_runtime": 299.3727, | |
| "eval_samples_per_second": 5.368, | |
| "eval_steps_per_second": 0.337, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_accuracy": 0.9691767171633182, | |
| "eval_f1": 0.7783425414364641, | |
| "eval_loss": 0.1701451987028122, | |
| "eval_precision": 0.8066880439761795, | |
| "eval_recall": 0.7519214346712212, | |
| "eval_runtime": 330.9586, | |
| "eval_samples_per_second": 4.856, | |
| "eval_steps_per_second": 0.305, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.475048126758478e-06, | |
| "loss": 0.0272, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.973239150346983, | |
| "eval_f1": 0.7797986932721173, | |
| "eval_loss": 0.11586667597293854, | |
| "eval_precision": 0.8071650520928533, | |
| "eval_recall": 0.7542271562766866, | |
| "eval_runtime": 326.8152, | |
| "eval_samples_per_second": 4.917, | |
| "eval_steps_per_second": 0.309, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.9719905922599957, | |
| "eval_f1": 0.7796919071382077, | |
| "eval_loss": 0.18351919949054718, | |
| "eval_precision": 0.7925893250992501, | |
| "eval_recall": 0.7672075149444919, | |
| "eval_runtime": 329.8149, | |
| "eval_samples_per_second": 4.872, | |
| "eval_steps_per_second": 0.306, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_accuracy": 0.9730095001280235, | |
| "eval_f1": 0.7893899204244033, | |
| "eval_loss": 0.14806130528450012, | |
| "eval_precision": 0.8183318056828598, | |
| "eval_recall": 0.7624252775405637, | |
| "eval_runtime": 319.7431, | |
| "eval_samples_per_second": 5.026, | |
| "eval_steps_per_second": 0.316, | |
| "step": 6400 | |
| } | |
| ], | |
| "max_steps": 7504, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.76412871737344e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |