--- RESUMING FROM: /home/skiredj.abderrahman/khalil/sbert_training/output/arabert_20260224_1730/checkpoint-102000 ---
{'loss': '0.2592', 'grad_norm': '3.323', 'learning_rate': '3.844e-06', 'epoch': '3.308'}
{'loss': '0.2543', 'grad_norm': '1.973', 'learning_rate': '3.808e-06', 'epoch': '3.315'}
{'loss': '0.2641', 'grad_norm': '4.95', 'learning_rate': '3.772e-06', 'epoch': '3.321'}
{'loss': '0.2435', 'grad_norm': '2.661', 'learning_rate': '3.736e-06', 'epoch': '3.328'}
{'loss': '0.251', 'grad_norm': '3.434', 'learning_rate': '3.7e-06', 'epoch': '3.334'}
{'loss': '0.2481', 'grad_norm': '2.562', 'learning_rate': '3.664e-06', 'epoch': '3.341'}
{'loss': '0.2627', 'grad_norm': '2.6', 'learning_rate': '3.628e-06', 'epoch': '3.347'}
{'loss': '0.248', 'grad_norm': '2.941', 'learning_rate': '3.592e-06', 'epoch': '3.354'}
{'loss': '0.2636', 'grad_norm': '2.153', 'learning_rate': '3.556e-06', 'epoch': '3.36'}
{'loss': '0.2619', 'grad_norm': '2.729', 'learning_rate': '3.52e-06', 'epoch': '3.366'}
{'loss': '0.2423', 'grad_norm': '2.413', 'learning_rate': '3.484e-06', 'epoch': '3.373'}
{'loss': '0.2505', 'grad_norm': '4.396', 'learning_rate': '3.448e-06', 'epoch': '3.379'}
{'loss': '0.2604', 'grad_norm': '3.629', 'learning_rate': '3.412e-06', 'epoch': '3.386'}
{'loss': '0.246', 'grad_norm': '5.426', 'learning_rate': '3.376e-06', 'epoch': '3.392'}
{'loss': '0.244', 'grad_norm': '1.848', 'learning_rate': '3.34e-06', 'epoch': '3.399'}
{'loss': '0.2641', 'grad_norm': '5.125', 'learning_rate': '3.304e-06', 'epoch': '3.405'}
{'loss': '0.2573', 'grad_norm': '3.377', 'learning_rate': '3.268e-06', 'epoch': '3.412'}
{'loss': '0.2613', 'grad_norm': '2.842', 'learning_rate': '3.232e-06', 'epoch': '3.418'}
{'loss': '0.2746', 'grad_norm': '3.197', 'learning_rate': '3.196e-06', 'epoch': '3.425'}
{'loss': '0.2578', 'grad_norm': '2.158', 'learning_rate': '3.16e-06', 'epoch': '3.431'}
{'loss': '0.2445', 'grad_norm': '2.634', 'learning_rate': '3.124e-06', 'epoch': '3.438'}
{'loss': '0.253', 'grad_norm': '2.139', 'learning_rate': '3.088e-06', 'epoch': '3.444'}
{'loss': '0.2644', 'grad_norm': '3.682', 'learning_rate': '3.052e-06', 'epoch': '3.451'}
{'loss': '0.2656', 'grad_norm': '4.607', 'learning_rate': '3.016e-06', 'epoch': '3.457'}
{'loss': '0.252', 'grad_norm': '2.139', 'learning_rate': '2.98e-06', 'epoch': '3.464'}
{'loss': '0.2527', 'grad_norm': '2.422', 'learning_rate': '2.944e-06', 'epoch': '3.47'}
{'loss': '0.2534', 'grad_norm': '3.598', 'learning_rate': '2.908e-06', 'epoch': '3.477'}
{'loss': '0.253', 'grad_norm': '1.388', 'learning_rate': '2.872e-06', 'epoch': '3.483'}
{'loss': '0.2614', 'grad_norm': '3.057', 'learning_rate': '2.837e-06', 'epoch': '3.489'}
{'loss': '0.2517', 'grad_norm': '2.296', 'learning_rate': '2.801e-06', 'epoch': '3.496'}
{'eval_train_loss': '0.2252', 'eval_dev-768_cosine_accuracy': '0.9849', 'eval_dev-512_cosine_accuracy': '0.9849', 'eval_dev-256_cosine_accuracy': '0.9851', 'eval_dev-128_cosine_accuracy': '0.9849', 'eval_dev-64_cosine_accuracy': '0.9841', 'eval_sequential_score': '0.9849', 'eval_train_runtime': '9737', 'eval_train_samples_per_second': '116', 'eval_train_steps_per_second': '14.5', 'epoch': '3.496'}
{'loss': '0.2589', 'grad_norm': '2.231', 'learning_rate': '2.765e-06', 'epoch': '3.502'}
{'loss': '0.2582', 'grad_norm': '5.077', 'learning_rate': '2.729e-06', 'epoch': '3.509'}
{'loss': '0.2553', 'grad_norm': '4.234', 'learning_rate': '2.693e-06', 'epoch': '3.515'}
{'loss': '0.2457', 'grad_norm': '2.167', 'learning_rate': '2.657e-06', 'epoch': '3.522'}
{'loss': '0.2662', 'grad_norm': '4.357', 'learning_rate': '2.621e-06', 'epoch': '3.528'}
{'loss': '0.2619', 'grad_norm': '3.987', 'learning_rate': '2.585e-06', 'epoch': '3.535'}
{'loss': '0.2556', 'grad_norm': '1.6', 'learning_rate': '2.549e-06', 'epoch': '3.541'}
{'loss': '0.2635', 'grad_norm': '2.069', 'learning_rate': '2.513e-06', 'epoch': '3.548'}
{'loss': '0.255', 'grad_norm': '2.314', 'learning_rate': '2.477e-06', 'epoch': '3.554'}
{'loss': '0.267', 'grad_norm': '4.255', 'learning_rate': '2.441e-06', 'epoch': '3.561'}
{'loss': '0.266', 'grad_norm': '3.208', 'learning_rate': '2.405e-06', 'epoch': '3.567'}
{'loss': '0.2604', 'grad_norm': '3.669', 'learning_rate': '2.369e-06', 'epoch': '3.574'}
{'loss': '0.2574', 'grad_norm': '3.103', 'learning_rate': '2.333e-06', 'epoch': '3.58'}
{'loss': '0.2607', 'grad_norm': '4.632', 'learning_rate': '2.297e-06', 'epoch': '3.587'}
{'loss': '0.2465', 'grad_norm': '4', 'learning_rate': '2.261e-06', 'epoch': '3.593'}
{'loss': '0.279', 'grad_norm': '3.647', 'learning_rate': '2.225e-06', 'epoch': '3.6'}
{'loss': '0.2681', 'grad_norm': '5.511', 'learning_rate': '2.189e-06', 'epoch': '3.606'}
{'loss': '0.2654', 'grad_norm': '1.217', 'learning_rate': '2.153e-06', 'epoch': '3.612'}
{'loss': '0.264', 'grad_norm': '4.641', 'learning_rate': '2.117e-06', 'epoch': '3.619'}
{'loss': '0.2774', 'grad_norm': '3.571', 'learning_rate': '2.081e-06', 'epoch': '3.625'}
{'loss': '0.2568', 'grad_norm': '3.808', 'learning_rate': '2.045e-06', 'epoch': '3.632'}
{'loss': '0.2665', 'grad_norm': '3.178', 'learning_rate': '2.009e-06', 'epoch': '3.638'}
{'loss': '0.2532', 'grad_norm': '1.566', 'learning_rate': '1.973e-06', 'epoch': '3.645'}
{'loss': '0.2613', 'grad_norm': '3.262', 'learning_rate': '1.937e-06', 'epoch': '3.651'}
{'loss': '0.2413', 'grad_norm': '4.082', 'learning_rate': '1.901e-06', 'epoch': '3.658'}
{'loss': '0.2788', 'grad_norm': '4.851', 'learning_rate': '1.865e-06', 'epoch': '3.664'}
{'loss': '0.2586', 'grad_norm': '5.756', 'learning_rate': '1.829e-06', 'epoch': '3.671'}
{'loss': '0.2602', 'grad_norm': '5.288', 'learning_rate': '1.793e-06', 'epoch': '3.677'}
{'loss': '0.2708', 'grad_norm': '3.492', 'learning_rate': '1.758e-06', 'epoch': '3.684'}
{'loss': '0.2556', 'grad_norm': '2.688', 'learning_rate': '1.722e-06', 'epoch': '3.69'}
{'eval_train_loss': '0.2188', 'eval_dev-768_cosine_accuracy': '0.9851', 'eval_dev-512_cosine_accuracy': '0.9852', 'eval_dev-256_cosine_accuracy': '0.9854', 'eval_dev-128_cosine_accuracy': '0.9853', 'eval_dev-64_cosine_accuracy': '0.9844', 'eval_sequential_score': '0.9851', 'eval_train_runtime': '9310', 'eval_train_samples_per_second': '121.3', 'eval_train_steps_per_second': '15.17', 'epoch': '3.69'}
{'loss': '0.2576', 'grad_norm': '2.428', 'learning_rate': '1.686e-06', 'epoch': '3.697'}
{'loss': '0.2713', 'grad_norm': '2.93', 'learning_rate': '1.65e-06', 'epoch': '3.703'}
{'loss': '0.2748', 'grad_norm': '3.659', 'learning_rate': '1.614e-06', 'epoch': '3.71'}
{'loss': '0.2542', 'grad_norm': '3.45', 'learning_rate': '1.578e-06', 'epoch': '3.716'}
{'loss': '0.2647', 'grad_norm': '4.824', 'learning_rate': '1.542e-06', 'epoch': '3.723'}
{'loss': '0.2751', 'grad_norm': '1.834', 'learning_rate': '1.506e-06', 'epoch': '3.729'}
{'loss': '0.2534', 'grad_norm': '4.17', 'learning_rate': '1.47e-06', 'epoch': '3.735'}
{'loss': '0.2577', 'grad_norm': '3.893', 'learning_rate': '1.434e-06', 'epoch': '3.742'}
{'loss': '0.2722', 'grad_norm': '4.691', 'learning_rate': '1.398e-06', 'epoch': '3.748'}
{'loss': '0.2717', 'grad_norm': '3.968', 'learning_rate': '1.362e-06', 'epoch': '3.755'}
{'loss': '0.2737', 'grad_norm': '4.474', 'learning_rate': '1.326e-06', 'epoch': '3.761'}
{'loss': '0.2725', 'grad_norm': '3.462', 'learning_rate': '1.29e-06', 'epoch': '3.768'}
{'loss': '0.2587', 'grad_norm': '1.857', 'learning_rate': '1.254e-06', 'epoch': '3.774'}
{'loss': '0.2623', 'grad_norm': '2.164', 'learning_rate': '1.218e-06', 'epoch': '3.781'}
{'loss': '0.2659', 'grad_norm': '2.674', 'learning_rate': '1.182e-06', 'epoch': '3.787'}
{'loss': '0.2735', 'grad_norm': '1.56', 'learning_rate': '1.146e-06', 'epoch': '3.794'}
{'loss': '0.2847', 'grad_norm': '4.402', 'learning_rate': '1.11e-06', 'epoch': '3.8'}
{'loss': '0.2636', 'grad_norm': '5.62', 'learning_rate': '1.074e-06', 'epoch': '3.807'}
{'loss': '0.2777', 'grad_norm': '4.51', 'learning_rate': '1.038e-06', 'epoch': '3.813'}
{'loss': '0.2751', 'grad_norm': '3.339', 'learning_rate': '1.002e-06', 'epoch': '3.82'}
{'loss': '0.2609', 'grad_norm': '3.817', 'learning_rate': '9.662e-07', 'epoch': '3.826'}
{'loss': '0.2684', 'grad_norm': '4.592', 'learning_rate': '9.303e-07', 'epoch': '3.833'}
{'loss': '0.2772', 'grad_norm': '2.499', 'learning_rate': '8.943e-07', 'epoch': '3.839'}
{'loss': '0.2684', 'grad_norm': '4.28', 'learning_rate': '8.583e-07', 'epoch': '3.846'}
{'loss': '0.2682', 'grad_norm': '3.179', 'learning_rate': '8.224e-07', 'epoch': '3.852'}
{'loss': '0.2784', 'grad_norm': '5.42', 'learning_rate': '7.864e-07', 'epoch': '3.858'}
{'loss': '0.2735', 'grad_norm': '2.668', 'learning_rate': '7.504e-07', 'epoch': '3.865'}
{'loss': '0.2848', 'grad_norm': '4.855', 'learning_rate': '7.145e-07', 'epoch': '3.871'}
{'loss': '0.2638', 'grad_norm': '2.601', 'learning_rate': '6.785e-07', 'epoch': '3.878'}
{'loss': '0.2711', 'grad_norm': '4.021', 'learning_rate': '6.425e-07', 'epoch': '3.884'}
{'eval_train_loss': '0.2171', 'eval_dev-768_cosine_accuracy': '0.9854', 'eval_dev-512_cosine_accuracy': '0.9855', 'eval_dev-256_cosine_accuracy': '0.9856', 'eval_dev-128_cosine_accuracy': '0.9855', 'eval_dev-64_cosine_accuracy': '0.9846', 'eval_sequential_score': '0.9854', 'eval_train_runtime': '9383', 'eval_train_samples_per_second': '120.4', 'eval_train_steps_per_second': '15.05', 'epoch': '3.884'}
{'loss': '0.2825', 'grad_norm': '2.434', 'learning_rate': '6.066e-07', 'epoch': '3.891'}
{'loss': '0.2724', 'grad_norm': '3.687', 'learning_rate': '5.706e-07', 'epoch': '3.897'}
{'loss': '0.3078', 'grad_norm': '5.537', 'learning_rate': '5.346e-07', 'epoch': '3.904'}
{'loss': '0.2806', 'grad_norm': '3.519', 'learning_rate': '4.987e-07', 'epoch': '3.91'}
{'loss': '0.2631', 'grad_norm': '3.982', 'learning_rate': '4.627e-07', 'epoch': '3.917'}
{'loss': '0.2892', 'grad_norm': '3.621', 'learning_rate': '4.267e-07', 'epoch': '3.923'}
{'loss': '0.2791', 'grad_norm': '4.467', 'learning_rate': '3.908e-07', 'epoch': '3.93'}
{'loss': '0.2874', 'grad_norm': '4.958', 'learning_rate': '3.548e-07', 'epoch': '3.936'}
{'loss': '0.2602', 'grad_norm': '3.852', 'learning_rate': '3.188e-07', 'epoch': '3.943'}
{'loss': '0.2988', 'grad_norm': '2.639', 'learning_rate': '2.829e-07', 'epoch': '3.949'}
{'loss': '0.2935', 'grad_norm': '1.878', 'learning_rate': '2.469e-07', 'epoch': '3.956'}
{'loss': '0.2999', 'grad_norm': '3.6', 'learning_rate': '2.109e-07', 'epoch': '3.962'}
{'loss': '0.293', 'grad_norm': '2.28', 'learning_rate': '1.75e-07', 'epoch': '3.969'}
{'loss': '0.2784', 'grad_norm': '4.347', 'learning_rate': '1.39e-07', 'epoch': '3.975'}
{'loss': '0.3013', 'grad_norm': '5.014', 'learning_rate': '1.03e-07', 'epoch': '3.982'}
{'loss': '0.2919', 'grad_norm': '2.171', 'learning_rate': '6.708e-08', 'epoch': '3.988'}
{'loss': '0.3011', 'grad_norm': '5.241', 'learning_rate': '3.111e-08', 'epoch': '3.994'}
{'train_runtime': '4.115e+04', 'train_samples_per_second': '384.4', 'train_steps_per_second': '3.003', 'train_loss': '0.04643', 'epoch': '4'}
model saved successfully