| { | |
| "best_metric": 1.177585244178772, | |
| "best_model_checkpoint": "/content/drive/Shareddrives/flipflow/Desarrollo/Projects/contrastive-product-matching/reports/contrastive-ft-siamese/all-xlarge-all-512-all-0.1-5e-05-frozen-roberta-base/0/checkpoint-25136", | |
| "epoch": 9.0, | |
| "global_step": 28278, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 7.829408020369192e-07, | |
| "loss": 1.7523, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.5786123488224062e-06, | |
| "loss": 1.6241, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.374283895607893e-06, | |
| "loss": 1.4901, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.1699554423933804e-06, | |
| "loss": 1.3765, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.965626989178867e-06, | |
| "loss": 1.2813, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.7612985359643546e-06, | |
| "loss": 1.2277, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.822340580767547, | |
| "eval_f1": 0.05583559519193486, | |
| "eval_loss": 1.2101483345031738, | |
| "eval_precision": 0.11464968152866242, | |
| "eval_recall": 0.03690415171706817, | |
| "eval_runtime": 113.1945, | |
| "eval_samples_per_second": 121.084, | |
| "eval_steps_per_second": 15.142, | |
| "step": 3142 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 5.556970082749841e-06, | |
| "loss": 1.204, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.3526416295353275e-06, | |
| "loss": 1.2103, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 7.148313176320815e-06, | |
| "loss": 1.1915, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 7.942393380012732e-06, | |
| "loss": 1.2112, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 8.738064926798218e-06, | |
| "loss": 1.1908, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 9.533736473583705e-06, | |
| "loss": 1.1902, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8191303078943528, | |
| "eval_f1": 0.05561904761904763, | |
| "eval_loss": 1.187880039215088, | |
| "eval_precision": 0.1083086053412463, | |
| "eval_recall": 0.03741670937980523, | |
| "eval_runtime": 105.6854, | |
| "eval_samples_per_second": 129.687, | |
| "eval_steps_per_second": 16.218, | |
| "step": 6284 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.0329408020369192e-05, | |
| "loss": 1.1958, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.112507956715468e-05, | |
| "loss": 1.1903, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1919159770846595e-05, | |
| "loss": 1.1805, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.271483131763208e-05, | |
| "loss": 1.1802, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.3510502864417568e-05, | |
| "loss": 1.1926, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.4306174411203055e-05, | |
| "loss": 1.1741, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4888370056909383, | |
| "eval_f1": 0.24259459459459462, | |
| "eval_loss": 1.1829431056976318, | |
| "eval_precision": 0.15371968762844226, | |
| "eval_recall": 0.5750896975909789, | |
| "eval_runtime": 105.5508, | |
| "eval_samples_per_second": 129.852, | |
| "eval_steps_per_second": 16.239, | |
| "step": 9426 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.5101845957988542e-05, | |
| "loss": 1.1848, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.589751750477403e-05, | |
| "loss": 1.1885, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.6693189051559517e-05, | |
| "loss": 1.178, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.7488860598345004e-05, | |
| "loss": 1.1823, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.828294080203692e-05, | |
| "loss": 1.1783, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.9078612348822408e-05, | |
| "loss": 1.1807, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 1.9874283895607895e-05, | |
| "loss": 1.1737, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4849700860936816, | |
| "eval_f1": 0.26993484331368295, | |
| "eval_loss": 1.1806172132492065, | |
| "eval_precision": 0.16908525524747345, | |
| "eval_recall": 0.6688877498718606, | |
| "eval_runtime": 105.6153, | |
| "eval_samples_per_second": 129.773, | |
| "eval_steps_per_second": 16.229, | |
| "step": 12568 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 2.0669955442393383e-05, | |
| "loss": 1.1733, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 2.14640356460853e-05, | |
| "loss": 1.1763, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.2258115849777213e-05, | |
| "loss": 1.1767, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.30537873965627e-05, | |
| "loss": 1.1891, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 2.3849458943348187e-05, | |
| "loss": 1.182, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 2.4645130490133675e-05, | |
| "loss": 1.1839, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.4106960455275062, | |
| "eval_f1": 0.25550742003871324, | |
| "eval_loss": 1.1798352003097534, | |
| "eval_precision": 0.1557653405259609, | |
| "eval_recall": 0.7104049205535623, | |
| "eval_runtime": 105.6302, | |
| "eval_samples_per_second": 129.755, | |
| "eval_steps_per_second": 16.226, | |
| "step": 15710 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.544080203691916e-05, | |
| "loss": 1.1756, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 2.6236473583704646e-05, | |
| "loss": 1.1727, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.7032145130490133e-05, | |
| "loss": 1.1892, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.782781667727562e-05, | |
| "loss": 1.1792, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2.8621896880967537e-05, | |
| "loss": 1.1858, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 2.941597708465945e-05, | |
| "loss": 1.1694, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.39085072231139645, | |
| "eval_f1": 0.25315323374183735, | |
| "eval_loss": 1.1799324750900269, | |
| "eval_precision": 0.15333766796705678, | |
| "eval_recall": 0.7252690927729369, | |
| "eval_runtime": 105.6599, | |
| "eval_samples_per_second": 129.718, | |
| "eval_steps_per_second": 16.222, | |
| "step": 18852 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 3.0211648631444938e-05, | |
| "loss": 1.1804, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 3.100732017823043e-05, | |
| "loss": 1.1857, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 3.1802991725015916e-05, | |
| "loss": 1.178, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 3.25986632718014e-05, | |
| "loss": 1.1785, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 3.339433481858688e-05, | |
| "loss": 1.1887, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 3.419000636537237e-05, | |
| "loss": 1.1636, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4095286735736174, | |
| "eval_f1": 0.255816091954023, | |
| "eval_loss": 1.1779592037200928, | |
| "eval_precision": 0.1558718063648588, | |
| "eval_recall": 0.7129677088672476, | |
| "eval_runtime": 105.6851, | |
| "eval_samples_per_second": 129.687, | |
| "eval_steps_per_second": 16.218, | |
| "step": 21994 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.498567791215786e-05, | |
| "loss": 1.1821, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 3.5778166772756204e-05, | |
| "loss": 1.1688, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 3.657383831954169e-05, | |
| "loss": 1.1845, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 3.736950986632718e-05, | |
| "loss": 1.1655, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 3.8165181413112666e-05, | |
| "loss": 1.19, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 3.896085295989816e-05, | |
| "loss": 1.184, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 3.975652450668365e-05, | |
| "loss": 1.1808, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.4719830731066686, | |
| "eval_f1": 0.26994855240593163, | |
| "eval_loss": 1.177585244178772, | |
| "eval_precision": 0.1680482290881688, | |
| "eval_recall": 0.6858021527421835, | |
| "eval_runtime": 105.6107, | |
| "eval_samples_per_second": 129.779, | |
| "eval_steps_per_second": 16.229, | |
| "step": 25136 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 4.0552196053469135e-05, | |
| "loss": 1.1774, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 4.134786760025462e-05, | |
| "loss": 1.1627, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 4.2141947803946535e-05, | |
| "loss": 1.1773, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 4.293761935073202e-05, | |
| "loss": 1.1902, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 4.373329089751751e-05, | |
| "loss": 1.1792, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.4528962444303e-05, | |
| "loss": 1.171, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.40989347730920767, | |
| "eval_f1": 0.2570273746095903, | |
| "eval_loss": 1.1790105104446411, | |
| "eval_precision": 0.1565752658086178, | |
| "eval_recall": 0.717068170169144, | |
| "eval_runtime": 105.7455, | |
| "eval_samples_per_second": 129.613, | |
| "eval_steps_per_second": 16.209, | |
| "step": 28278 | |
| } | |
| ], | |
| "max_steps": 628400, | |
| "num_train_epochs": 200, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |