{ "best_metric": null, "best_model_checkpoint": null, "epoch": 100.0, "eval_steps": 500, "global_step": 10600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.2873680591583252, "learning_rate": 4.9500000000000004e-05, "loss": 1.247, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.7410362362861633, "eval_overall_accuracy": 0.8352737181075056, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.371, "eval_samples_per_second": 504.108, "eval_steps_per_second": 8.087, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.251749873161316, "learning_rate": 4.9e-05, "loss": 0.7131, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.012738853503184716, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.25, "eval_PERSON_recall": 0.006535947712418301, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.6369233727455139, "eval_overall_accuracy": 0.8362645528858063, "eval_overall_f1": 0.005681818181818181, "eval_overall_precision": 0.16666666666666666, "eval_overall_recall": 0.002890173410404624, "eval_runtime": 0.3741, "eval_samples_per_second": 499.916, "eval_steps_per_second": 8.02, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.4780464172363281, "learning_rate": 4.85e-05, "loss": 0.629, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.07954545454545454, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.30434782608695654, "eval_PERSON_recall": 0.0457516339869281, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 31, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.5407068729400635, "eval_overall_accuracy": 0.8424572702501858, "eval_overall_f1": 0.03674540682414699, "eval_overall_precision": 0.2, "eval_overall_recall": 0.02023121387283237, "eval_runtime": 0.3721, "eval_samples_per_second": 502.555, "eval_steps_per_second": 8.062, "step": 318 }, { "epoch": 4.0, "grad_norm": 2.4032466411590576, "learning_rate": 4.8e-05, "loss": 0.5381, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.10389610389610389, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5, "eval_LOCATION_recall": 0.057971014492753624, "eval_ORGANIZATION_f1": 0.028169014084507043, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.1, "eval_ORGANIZATION_recall": 0.01639344262295082, "eval_PERSON_f1": 0.23236514522821577, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.3181818181818182, "eval_PERSON_recall": 0.1830065359477124, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.2857142857142857, "eval_TIME_number": 31, "eval_TIME_precision": 0.3888888888888889, "eval_TIME_recall": 0.22580645161290322, "eval_loss": 0.4457257091999054, "eval_overall_accuracy": 0.8667327223185534, "eval_overall_f1": 0.1702127659574468, "eval_overall_precision": 0.3225806451612903, "eval_overall_recall": 0.11560693641618497, "eval_runtime": 0.3729, "eval_samples_per_second": 501.455, "eval_steps_per_second": 8.045, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.463838815689087, "learning_rate": 4.75e-05, "loss": 0.4387, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.34951456310679613, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5294117647058824, "eval_LOCATION_recall": 0.2608695652173913, "eval_ORGANIZATION_f1": 0.16470588235294117, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.2916666666666667, "eval_ORGANIZATION_recall": 0.11475409836065574, "eval_PERSON_f1": 0.5243902439024392, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.49142857142857144, "eval_PERSON_recall": 0.5620915032679739, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.45283018867924524, "eval_TIME_number": 31, "eval_TIME_precision": 0.5454545454545454, "eval_TIME_recall": 0.3870967741935484, "eval_loss": 0.3568115234375, "eval_overall_accuracy": 0.8957146395838494, "eval_overall_f1": 0.4026186579378069, "eval_overall_precision": 0.4641509433962264, "eval_overall_recall": 0.3554913294797688, "eval_runtime": 0.3737, "eval_samples_per_second": 500.37, "eval_steps_per_second": 8.027, "step": 530 }, { "epoch": 6.0, "grad_norm": 9.46357250213623, "learning_rate": 4.7e-05, "loss": 0.3593, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.4671532846715329, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.47058823529411764, "eval_LOCATION_recall": 0.463768115942029, "eval_ORGANIZATION_f1": 0.39285714285714285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.43137254901960786, "eval_ORGANIZATION_recall": 0.36065573770491804, "eval_PERSON_f1": 0.711764705882353, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.6470588235294118, "eval_PERSON_recall": 0.7908496732026143, "eval_QUANTITY_f1": 0.3389830508474576, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.37037037037037035, "eval_QUANTITY_recall": 0.3125, "eval_TIME_f1": 0.6666666666666667, "eval_TIME_number": 31, "eval_TIME_precision": 0.65625, "eval_TIME_recall": 0.6774193548387096, "eval_loss": 0.2867273986339569, "eval_overall_accuracy": 0.9227148872925439, "eval_overall_f1": 0.5794655414908579, "eval_overall_precision": 0.5643835616438356, "eval_overall_recall": 0.5953757225433526, "eval_runtime": 0.3704, "eval_samples_per_second": 504.858, "eval_steps_per_second": 8.099, "step": 636 }, { "epoch": 7.0, "grad_norm": 0.9221069812774658, "learning_rate": 4.6500000000000005e-05, "loss": 0.296, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.5827814569536424, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.5365853658536586, "eval_LOCATION_recall": 0.6376811594202898, "eval_ORGANIZATION_f1": 0.45925925925925926, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4189189189189189, "eval_ORGANIZATION_recall": 0.5081967213114754, "eval_PERSON_f1": 0.8176470588235294, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7433155080213903, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.463768115942029, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.43243243243243246, "eval_QUANTITY_recall": 0.5, "eval_TIME_f1": 0.6567164179104478, "eval_TIME_number": 31, "eval_TIME_precision": 0.6111111111111112, "eval_TIME_recall": 0.7096774193548387, "eval_loss": 0.24547956883907318, "eval_overall_accuracy": 0.9316324002972505, "eval_overall_f1": 0.6614173228346456, "eval_overall_precision": 0.6057692307692307, "eval_overall_recall": 0.7283236994219653, "eval_runtime": 0.3744, "eval_samples_per_second": 499.493, "eval_steps_per_second": 8.013, "step": 742 }, { "epoch": 8.0, "grad_norm": 1.383445143699646, "learning_rate": 4.600000000000001e-05, "loss": 0.254, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.7006369426751592, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.625, "eval_LOCATION_recall": 0.7971014492753623, "eval_ORGANIZATION_f1": 0.5100671140939597, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4318181818181818, "eval_ORGANIZATION_recall": 0.6229508196721312, "eval_PERSON_f1": 0.8249258160237388, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7554347826086957, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.45714285714285713, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.42105263157894735, "eval_QUANTITY_recall": 0.5, "eval_TIME_f1": 0.7575757575757576, "eval_TIME_number": 31, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.2185853123664856, "eval_overall_accuracy": 0.9375774089670548, "eval_overall_f1": 0.7008985879332478, "eval_overall_precision": 0.6304849884526559, "eval_overall_recall": 0.7890173410404624, "eval_runtime": 0.3742, "eval_samples_per_second": 499.789, "eval_steps_per_second": 8.018, "step": 848 }, { "epoch": 9.0, "grad_norm": 1.6789393424987793, "learning_rate": 4.55e-05, "loss": 0.2277, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7215189873417721, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6404494382022472, "eval_LOCATION_recall": 0.8260869565217391, "eval_ORGANIZATION_f1": 0.5342465753424658, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.4588235294117647, "eval_ORGANIZATION_recall": 0.639344262295082, "eval_PERSON_f1": 0.8358208955223881, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7692307692307693, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.5142857142857142, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.47368421052631576, "eval_QUANTITY_recall": 0.5625, "eval_TIME_f1": 0.7812499999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7575757575757576, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.1994231939315796, "eval_overall_accuracy": 0.9403022046073817, "eval_overall_f1": 0.7218628719275549, "eval_overall_precision": 0.6533957845433255, "eval_overall_recall": 0.8063583815028902, "eval_runtime": 0.3766, "eval_samples_per_second": 496.499, "eval_steps_per_second": 7.965, "step": 954 }, { "epoch": 10.0, "grad_norm": 1.1687356233596802, "learning_rate": 4.5e-05, "loss": 0.2071, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7712418300653594, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7023809523809523, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.5430463576158939, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.45555555555555555, "eval_ORGANIZATION_recall": 0.6721311475409836, "eval_PERSON_f1": 0.8398791540785498, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7808988764044944, "eval_PERSON_recall": 0.9084967320261438, "eval_QUANTITY_f1": 0.5507246376811593, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5135135135135135, "eval_QUANTITY_recall": 0.59375, "eval_TIME_f1": 0.7999999999999999, "eval_TIME_number": 31, "eval_TIME_precision": 0.7647058823529411, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1809079945087433, "eval_overall_accuracy": 0.9427792915531336, "eval_overall_f1": 0.7386215864759428, "eval_overall_precision": 0.6713947990543735, "eval_overall_recall": 0.8208092485549133, "eval_runtime": 0.3749, "eval_samples_per_second": 498.839, "eval_steps_per_second": 8.003, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.9759888648986816, "learning_rate": 4.4500000000000004e-05, "loss": 0.1937, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7692307692307693, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6896551724137931, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.5931034482758619, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5119047619047619, "eval_ORGANIZATION_recall": 0.7049180327868853, "eval_PERSON_f1": 0.8459214501510575, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7865168539325843, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.7575757575757576, "eval_TIME_number": 31, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.17153412103652954, "eval_overall_accuracy": 0.9455040871934605, "eval_overall_f1": 0.7526041666666667, "eval_overall_precision": 0.6848341232227488, "eval_overall_recall": 0.8352601156069365, "eval_runtime": 0.377, "eval_samples_per_second": 496.013, "eval_steps_per_second": 7.957, "step": 1166 }, { "epoch": 12.0, "grad_norm": 2.159359931945801, "learning_rate": 4.4000000000000006e-05, "loss": 0.183, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7792207792207793, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7058823529411765, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.5957446808510638, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.525, "eval_ORGANIZATION_recall": 0.6885245901639344, "eval_PERSON_f1": 0.8484848484848484, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.7909604519774012, "eval_PERSON_recall": 0.9150326797385621, "eval_QUANTITY_f1": 0.6, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.746268656716418, "eval_TIME_number": 31, "eval_TIME_precision": 0.6944444444444444, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.16189619898796082, "eval_overall_accuracy": 0.9479811741392122, "eval_overall_f1": 0.7559055118110236, "eval_overall_precision": 0.6923076923076923, "eval_overall_recall": 0.8323699421965318, "eval_runtime": 0.3748, "eval_samples_per_second": 498.956, "eval_steps_per_second": 8.005, "step": 1272 }, { "epoch": 13.0, "grad_norm": 1.0158612728118896, "learning_rate": 4.35e-05, "loss": 0.1739, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6068965517241379, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5238095238095238, "eval_ORGANIZATION_recall": 0.7213114754098361, "eval_PERSON_f1": 0.8571428571428571, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8011363636363636, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.5797101449275363, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5405405405405406, "eval_QUANTITY_recall": 0.625, "eval_TIME_f1": 0.746268656716418, "eval_TIME_number": 31, "eval_TIME_precision": 0.6944444444444444, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.15490159392356873, "eval_overall_accuracy": 0.9512013871686896, "eval_overall_f1": 0.7601572739187418, "eval_overall_precision": 0.6954436450839329, "eval_overall_recall": 0.838150289017341, "eval_runtime": 0.372, "eval_samples_per_second": 502.659, "eval_steps_per_second": 8.064, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.7819868326187134, "learning_rate": 4.3e-05, "loss": 0.1665, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5444444444444444, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.626865671641791, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 31, "eval_TIME_precision": 0.7352941176470589, "eval_TIME_recall": 0.8064516129032258, "eval_loss": 0.15250568091869354, "eval_overall_accuracy": 0.9529353480307159, "eval_overall_f1": 0.7789473684210526, "eval_overall_precision": 0.714975845410628, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3746, "eval_samples_per_second": 499.251, "eval_steps_per_second": 8.009, "step": 1484 }, { "epoch": 15.0, "grad_norm": 0.672570526599884, "learning_rate": 4.25e-05, "loss": 0.1598, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6206896551724138, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5357142857142857, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.7647058823529411, "eval_TIME_number": 31, "eval_TIME_precision": 0.7027027027027027, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.15064987540245056, "eval_overall_accuracy": 0.9524399306415655, "eval_overall_f1": 0.7752956636005256, "eval_overall_precision": 0.7108433734939759, "eval_overall_recall": 0.8526011560693642, "eval_runtime": 0.3752, "eval_samples_per_second": 498.368, "eval_steps_per_second": 7.995, "step": 1590 }, { "epoch": 16.0, "grad_norm": 0.6825155019760132, "learning_rate": 4.2e-05, "loss": 0.1549, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6388888888888888, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5542168674698795, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.626865671641791, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6, "eval_QUANTITY_recall": 0.65625, "eval_TIME_f1": 0.782608695652174, "eval_TIME_number": 31, "eval_TIME_precision": 0.7105263157894737, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.1479189395904541, "eval_overall_accuracy": 0.9536784741144414, "eval_overall_f1": 0.7799736495388669, "eval_overall_precision": 0.7167070217917676, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3703, "eval_samples_per_second": 505.025, "eval_steps_per_second": 8.102, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.8551343083381653, "learning_rate": 4.15e-05, "loss": 0.1487, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7741935483870968, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6976744186046512, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.64, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5393258426966292, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6857142857142857, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.782608695652174, "eval_TIME_number": 31, "eval_TIME_precision": 0.7105263157894737, "eval_TIME_recall": 0.8709677419354839, "eval_loss": 0.14963936805725098, "eval_overall_accuracy": 0.9534307654198663, "eval_overall_f1": 0.7808041504539559, "eval_overall_precision": 0.7082352941176471, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3724, "eval_samples_per_second": 502.152, "eval_steps_per_second": 8.056, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.5059446096420288, "learning_rate": 4.1e-05, "loss": 0.1471, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6394557823129252, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5465116279069767, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6376811594202898, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.6875, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1425521969795227, "eval_overall_accuracy": 0.9556601436710429, "eval_overall_f1": 0.7748691099476441, "eval_overall_precision": 0.7081339712918661, "eval_overall_recall": 0.8554913294797688, "eval_runtime": 0.3712, "eval_samples_per_second": 503.811, "eval_steps_per_second": 8.083, "step": 1908 }, { "epoch": 19.0, "grad_norm": 1.4319778680801392, "learning_rate": 4.05e-05, "loss": 0.1415, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.8079470198675496, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.652482269503546, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.575, "eval_ORGANIZATION_recall": 0.7540983606557377, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.7428571428571428, "eval_TIME_number": 31, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8387096774193549, "eval_loss": 0.1388433575630188, "eval_overall_accuracy": 0.9568986871439188, "eval_overall_f1": 0.7915567282321899, "eval_overall_precision": 0.7281553398058253, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3716, "eval_samples_per_second": 503.244, "eval_steps_per_second": 8.073, "step": 2014 }, { "epoch": 20.0, "grad_norm": 0.6436260342597961, "learning_rate": 4e-05, "loss": 0.1385, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.7870967741935485, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6575342465753424, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5647058823529412, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8606060606060606, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8022598870056498, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8, "eval_TIME_number": 31, "eval_TIME_precision": 0.717948717948718, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1451817750930786, "eval_overall_accuracy": 0.9546693088927422, "eval_overall_f1": 0.7922077922077921, "eval_overall_precision": 0.7193396226415094, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3763, "eval_samples_per_second": 496.942, "eval_steps_per_second": 7.972, "step": 2120 }, { "epoch": 21.0, "grad_norm": 0.9739159941673279, "learning_rate": 3.9500000000000005e-05, "loss": 0.1361, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7712418300653594, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7023809523809523, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6442953020134228, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5454545454545454, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7164179104477612, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6857142857142857, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14020903408527374, "eval_overall_accuracy": 0.955907852365618, "eval_overall_f1": 0.7879581151832461, "eval_overall_precision": 0.7200956937799043, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3722, "eval_samples_per_second": 502.459, "eval_steps_per_second": 8.061, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.1439884901046753, "learning_rate": 3.9000000000000006e-05, "loss": 0.1361, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7973856209150327, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.64, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5393258426966292, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.8115942028985507, "eval_TIME_number": 31, "eval_TIME_precision": 0.7368421052631579, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14226193726062775, "eval_overall_accuracy": 0.9549170175873173, "eval_overall_f1": 0.7963446475195822, "eval_overall_precision": 0.7261904761904762, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3724, "eval_samples_per_second": 502.146, "eval_steps_per_second": 8.056, "step": 2332 }, { "epoch": 23.0, "grad_norm": 0.9229549765586853, "learning_rate": 3.85e-05, "loss": 0.1331, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6474820143884893, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5769230769230769, "eval_ORGANIZATION_recall": 0.7377049180327869, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13378849625587463, "eval_overall_accuracy": 0.9581372306167947, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7425742574257426, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3737, "eval_samples_per_second": 500.418, "eval_steps_per_second": 8.028, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.7910873889923096, "learning_rate": 3.8e-05, "loss": 0.1286, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7741935483870968, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.6976744186046512, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6621621621621622, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5632183908045977, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7222222222222223, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.65, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.7887323943661972, "eval_TIME_number": 31, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1469903588294983, "eval_overall_accuracy": 0.9544216001981669, "eval_overall_f1": 0.7911802853437094, "eval_overall_precision": 0.7176470588235294, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3719, "eval_samples_per_second": 502.77, "eval_steps_per_second": 8.066, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.3032689094543457, "learning_rate": 3.7500000000000003e-05, "loss": 0.1274, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7843137254901961, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6620689655172414, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8676923076923077, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8197674418604651, "eval_PERSON_recall": 0.9215686274509803, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8115942028985507, "eval_TIME_number": 31, "eval_TIME_precision": 0.7368421052631579, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13992294669151306, "eval_overall_accuracy": 0.9566509784493435, "eval_overall_f1": 0.7936925098554534, "eval_overall_precision": 0.727710843373494, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3712, "eval_samples_per_second": 503.751, "eval_steps_per_second": 8.082, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.104667067527771, "learning_rate": 3.7e-05, "loss": 0.1269, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.8026315789473685, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5444444444444444, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.14159581065177917, "eval_overall_accuracy": 0.9556601436710429, "eval_overall_f1": 0.7989556135770234, "eval_overall_precision": 0.7285714285714285, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3741, "eval_samples_per_second": 499.897, "eval_steps_per_second": 8.02, "step": 2756 }, { "epoch": 27.0, "grad_norm": 3.7249088287353516, "learning_rate": 3.65e-05, "loss": 0.1242, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7763157894736842, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7108433734939759, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6857142857142857, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6075949367088608, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8685015290519879, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8160919540229885, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13718503713607788, "eval_overall_accuracy": 0.9568986871439188, "eval_overall_f1": 0.8015873015873016, "eval_overall_precision": 0.7390243902439024, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3743, "eval_samples_per_second": 499.541, "eval_steps_per_second": 8.014, "step": 2862 }, { "epoch": 28.0, "grad_norm": 4.685704231262207, "learning_rate": 3.6e-05, "loss": 0.1223, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.8187919463087248, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7625, "eval_LOCATION_recall": 0.8840579710144928, "eval_ORGANIZATION_f1": 0.6619718309859155, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5802469135802469, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1325845867395401, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8095872170439414, "eval_overall_precision": 0.7506172839506173, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3723, "eval_samples_per_second": 502.217, "eval_steps_per_second": 8.057, "step": 2968 }, { "epoch": 29.0, "grad_norm": 3.4481709003448486, "learning_rate": 3.55e-05, "loss": 0.1193, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6762589928057554, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6025641025641025, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8819875776397514, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8402366863905325, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7647058823529411, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7222222222222222, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1309487521648407, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8112449799196787, "eval_overall_precision": 0.7556109725685786, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3737, "eval_samples_per_second": 500.387, "eval_steps_per_second": 8.028, "step": 3074 }, { "epoch": 30.0, "grad_norm": 0.7676149606704712, "learning_rate": 3.5e-05, "loss": 0.119, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.8053691275167786, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5875, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13215813040733337, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8090787716955942, "eval_overall_precision": 0.7518610421836228, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3736, "eval_samples_per_second": 500.504, "eval_steps_per_second": 8.029, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.5464662313461304, "learning_rate": 3.45e-05, "loss": 0.1208, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13540008664131165, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.8010610079575597, "eval_overall_precision": 0.7401960784313726, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3719, "eval_samples_per_second": 502.807, "eval_steps_per_second": 8.066, "step": 3286 }, { "epoch": 32.0, "grad_norm": 1.3645358085632324, "learning_rate": 3.4000000000000007e-05, "loss": 0.1143, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6573426573426574, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.573170731707317, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7462686567164178, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7142857142857143, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13142676651477814, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.8026666666666668, "eval_overall_precision": 0.745049504950495, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3729, "eval_samples_per_second": 501.416, "eval_steps_per_second": 8.044, "step": 3392 }, { "epoch": 33.0, "grad_norm": 1.6423691511154175, "learning_rate": 3.35e-05, "loss": 0.1151, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7947019867549668, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7317073170731707, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6620689655172414, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.132831409573555, "eval_overall_accuracy": 0.9591280653950953, "eval_overall_f1": 0.797886393659181, "eval_overall_precision": 0.7347931873479319, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3744, "eval_samples_per_second": 499.492, "eval_steps_per_second": 8.013, "step": 3498 }, { "epoch": 34.0, "grad_norm": 0.8335278630256653, "learning_rate": 3.3e-05, "loss": 0.1121, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7407407407407407, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6533333333333333, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.550561797752809, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13941965997219086, "eval_overall_accuracy": 0.9571463958384939, "eval_overall_f1": 0.8031496062992126, "eval_overall_precision": 0.7355769230769231, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.375, "eval_samples_per_second": 498.612, "eval_steps_per_second": 7.999, "step": 3604 }, { "epoch": 35.0, "grad_norm": 2.70279598236084, "learning_rate": 3.2500000000000004e-05, "loss": 0.1149, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6486486486486487, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5517241379310345, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13413338363170624, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8031704095112285, "eval_overall_precision": 0.7396593673965937, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3724, "eval_samples_per_second": 502.185, "eval_steps_per_second": 8.056, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.7904542684555054, "learning_rate": 3.2000000000000005e-05, "loss": 0.1114, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6857142857142857, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6075949367088608, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8854489164086689, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8411764705882353, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12858277559280396, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8112449799196787, "eval_overall_precision": 0.7556109725685786, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3711, "eval_samples_per_second": 503.902, "eval_steps_per_second": 8.084, "step": 3816 }, { "epoch": 37.0, "grad_norm": 1.3650281429290771, "learning_rate": 3.15e-05, "loss": 0.1092, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6805555555555556, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5903614457831325, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13275323808193207, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8068783068783069, "eval_overall_precision": 0.7439024390243902, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3737, "eval_samples_per_second": 500.384, "eval_steps_per_second": 8.028, "step": 3922 }, { "epoch": 38.0, "grad_norm": 1.638619065284729, "learning_rate": 3.1e-05, "loss": 0.1072, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.133976012468338, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8068783068783069, "eval_overall_precision": 0.7439024390243902, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3719, "eval_samples_per_second": 502.881, "eval_steps_per_second": 8.068, "step": 4028 }, { "epoch": 39.0, "grad_norm": 0.7919366955757141, "learning_rate": 3.05e-05, "loss": 0.1032, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6713286713286712, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1285211592912674, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.804780876494024, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3722, "eval_samples_per_second": 502.429, "eval_steps_per_second": 8.06, "step": 4134 }, { "epoch": 40.0, "grad_norm": 1.121160626411438, "learning_rate": 3e-05, "loss": 0.1045, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.676056338028169, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5925925925925926, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12849295139312744, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8058510638297872, "eval_overall_precision": 0.7463054187192119, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3741, "eval_samples_per_second": 499.806, "eval_steps_per_second": 8.018, "step": 4240 }, { "epoch": 41.0, "grad_norm": 1.5202959775924683, "learning_rate": 2.95e-05, "loss": 0.1057, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13106106221675873, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8084544253632759, "eval_overall_precision": 0.7445255474452555, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3742, "eval_samples_per_second": 499.683, "eval_steps_per_second": 8.016, "step": 4346 }, { "epoch": 42.0, "grad_norm": 1.6630405187606812, "learning_rate": 2.9e-05, "loss": 0.104, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.684931506849315, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8834355828220859, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8323699421965318, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1322728544473648, "eval_overall_accuracy": 0.9588803567005202, "eval_overall_f1": 0.8100263852242744, "eval_overall_precision": 0.7451456310679612, "eval_overall_recall": 0.8872832369942196, "eval_runtime": 0.3728, "eval_samples_per_second": 501.676, "eval_steps_per_second": 8.048, "step": 4452 }, { "epoch": 43.0, "grad_norm": 1.8563308715820312, "learning_rate": 2.8499999999999998e-05, "loss": 0.1066, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7837837837837838, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7341772151898734, "eval_LOCATION_recall": 0.8405797101449275, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1353512555360794, "eval_overall_accuracy": 0.9583849393113698, "eval_overall_f1": 0.8079470198675497, "eval_overall_precision": 0.7457212713936431, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3756, "eval_samples_per_second": 497.827, "eval_steps_per_second": 7.987, "step": 4558 }, { "epoch": 44.0, "grad_norm": 1.7642518281936646, "learning_rate": 2.8000000000000003e-05, "loss": 0.1046, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6714285714285714, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1240304633975029, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7425742574257426, "eval_overall_recall": 0.8670520231213873, "eval_runtime": 0.3715, "eval_samples_per_second": 503.309, "eval_steps_per_second": 8.074, "step": 4664 }, { "epoch": 45.0, "grad_norm": 1.239845871925354, "learning_rate": 2.7500000000000004e-05, "loss": 0.102, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.7972972972972974, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7468354430379747, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12775897979736328, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8095872170439414, "eval_overall_precision": 0.7506172839506173, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3743, "eval_samples_per_second": 499.627, "eval_steps_per_second": 8.015, "step": 4770 }, { "epoch": 46.0, "grad_norm": 6.3992600440979, "learning_rate": 2.7000000000000002e-05, "loss": 0.101, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8746177370030581, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8218390804597702, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1305726170539856, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8073878627968338, "eval_overall_precision": 0.7427184466019418, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3711, "eval_samples_per_second": 503.952, "eval_steps_per_second": 8.085, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.040471076965332, "learning_rate": 2.6500000000000004e-05, "loss": 0.1002, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5783132530120482, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1305668205022812, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8042328042328042, "eval_overall_precision": 0.7414634146341463, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3752, "eval_samples_per_second": 498.426, "eval_steps_per_second": 7.996, "step": 4982 }, { "epoch": 48.0, "grad_norm": 2.8856351375579834, "learning_rate": 2.6000000000000002e-05, "loss": 0.0994, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8108108108108109, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.759493670886076, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6482758620689655, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5595238095238095, "eval_ORGANIZATION_recall": 0.7704918032786885, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13150662183761597, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.8015873015873016, "eval_overall_precision": 0.7390243902439024, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3732, "eval_samples_per_second": 501.099, "eval_steps_per_second": 8.039, "step": 5088 }, { "epoch": 49.0, "grad_norm": 3.1868813037872314, "learning_rate": 2.5500000000000003e-05, "loss": 0.0995, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.8163265306122449, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7692307692307693, "eval_LOCATION_recall": 0.8695652173913043, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12851661443710327, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8095872170439414, "eval_overall_precision": 0.7506172839506173, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3781, "eval_samples_per_second": 494.575, "eval_steps_per_second": 7.934, "step": 5194 }, { "epoch": 50.0, "grad_norm": 1.8704575300216675, "learning_rate": 2.5e-05, "loss": 0.0981, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6808510638297871, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1275041401386261, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.8010610079575597, "eval_overall_precision": 0.7401960784313726, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.371, "eval_samples_per_second": 504.005, "eval_steps_per_second": 8.086, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.2837458848953247, "learning_rate": 2.45e-05, "loss": 0.0966, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8861538461538462, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8372093023255814, "eval_PERSON_recall": 0.9411764705882353, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12873469293117523, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8084544253632759, "eval_overall_precision": 0.7445255474452555, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3726, "eval_samples_per_second": 501.893, "eval_steps_per_second": 8.052, "step": 5406 }, { "epoch": 52.0, "grad_norm": 0.7324889898300171, "learning_rate": 2.4e-05, "loss": 0.0963, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8746177370030581, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8218390804597702, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12882520258426666, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8084544253632759, "eval_overall_precision": 0.7445255474452555, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3724, "eval_samples_per_second": 502.128, "eval_steps_per_second": 8.056, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.6753724813461304, "learning_rate": 2.35e-05, "loss": 0.098, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6857142857142857, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12833988666534424, "eval_overall_accuracy": 0.9593757740896706, "eval_overall_f1": 0.7999999999999999, "eval_overall_precision": 0.7383863080684596, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3712, "eval_samples_per_second": 503.796, "eval_steps_per_second": 8.082, "step": 5618 }, { "epoch": 54.0, "grad_norm": 1.8212159872055054, "learning_rate": 2.3000000000000003e-05, "loss": 0.095, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6857142857142857, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1265900731086731, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8079999999999999, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3725, "eval_samples_per_second": 502.02, "eval_steps_per_second": 8.054, "step": 5724 }, { "epoch": 55.0, "grad_norm": 2.103760242462158, "learning_rate": 2.25e-05, "loss": 0.0963, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13048739731311798, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8095238095238094, "eval_overall_precision": 0.7463414634146341, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3735, "eval_samples_per_second": 500.645, "eval_steps_per_second": 8.032, "step": 5830 }, { "epoch": 56.0, "grad_norm": 1.7916220426559448, "learning_rate": 2.2000000000000003e-05, "loss": 0.0945, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7194244604316549, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6410256410256411, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6857142857142857, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12367260456085205, "eval_overall_accuracy": 0.9625959871191478, "eval_overall_f1": 0.8101604278074866, "eval_overall_precision": 0.753731343283582, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3729, "eval_samples_per_second": 501.411, "eval_steps_per_second": 8.044, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.4273295402526855, "learning_rate": 2.15e-05, "loss": 0.0944, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12745532393455505, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8105960264900662, "eval_overall_precision": 0.7481662591687042, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3724, "eval_samples_per_second": 502.154, "eval_steps_per_second": 8.056, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.433877557516098, "learning_rate": 2.1e-05, "loss": 0.094, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7142857142857143, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6329113924050633, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12492260336875916, "eval_overall_accuracy": 0.9621005697299975, "eval_overall_f1": 0.8122503328894806, "eval_overall_precision": 0.7530864197530864, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3718, "eval_samples_per_second": 502.971, "eval_steps_per_second": 8.069, "step": 6148 }, { "epoch": 59.0, "grad_norm": 0.6837877035140991, "learning_rate": 2.05e-05, "loss": 0.0927, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7536231884057971, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.7027027027027027, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12483343482017517, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8116710875331565, "eval_overall_precision": 0.75, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3719, "eval_samples_per_second": 502.848, "eval_steps_per_second": 8.067, "step": 6254 }, { "epoch": 60.0, "grad_norm": 0.7817451357841492, "learning_rate": 2e-05, "loss": 0.0928, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12917159497737885, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8095238095238094, "eval_overall_precision": 0.7463414634146341, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.372, "eval_samples_per_second": 502.631, "eval_steps_per_second": 8.064, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.9623644351959229, "learning_rate": 1.9500000000000003e-05, "loss": 0.0931, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12796209752559662, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8026490066225165, "eval_overall_precision": 0.7408312958435208, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3707, "eval_samples_per_second": 504.472, "eval_steps_per_second": 8.093, "step": 6466 }, { "epoch": 62.0, "grad_norm": 1.2388701438903809, "learning_rate": 1.9e-05, "loss": 0.0894, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.127840057015419, "eval_overall_accuracy": 0.9598711914788209, "eval_overall_f1": 0.8052980132450333, "eval_overall_precision": 0.7432762836185819, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3746, "eval_samples_per_second": 499.163, "eval_steps_per_second": 8.008, "step": 6572 }, { "epoch": 63.0, "grad_norm": 2.133678913116455, "learning_rate": 1.85e-05, "loss": 0.0911, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5783132530120482, "eval_ORGANIZATION_recall": 0.7868852459016393, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.71875, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1259499192237854, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.7984084880636606, "eval_overall_precision": 0.7377450980392157, "eval_overall_recall": 0.869942196531792, "eval_runtime": 0.3802, "eval_samples_per_second": 491.903, "eval_steps_per_second": 7.891, "step": 6678 }, { "epoch": 64.0, "grad_norm": 1.4753077030181885, "learning_rate": 1.8e-05, "loss": 0.0889, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8800000000000001, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8313953488372093, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12907566130161285, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8068783068783069, "eval_overall_precision": 0.7439024390243902, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3721, "eval_samples_per_second": 502.538, "eval_steps_per_second": 8.062, "step": 6784 }, { "epoch": 65.0, "grad_norm": 1.000364065170288, "learning_rate": 1.75e-05, "loss": 0.0884, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7092198581560285, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.625, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8746177370030581, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8218390804597702, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12756387889385223, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8095238095238094, "eval_overall_precision": 0.7463414634146341, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3751, "eval_samples_per_second": 498.558, "eval_steps_per_second": 7.998, "step": 6890 }, { "epoch": 66.0, "grad_norm": 1.3308097124099731, "learning_rate": 1.7000000000000003e-05, "loss": 0.0905, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12825970351696014, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8068783068783069, "eval_overall_precision": 0.7439024390243902, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3714, "eval_samples_per_second": 503.45, "eval_steps_per_second": 8.077, "step": 6996 }, { "epoch": 67.0, "grad_norm": 1.1464766263961792, "learning_rate": 1.65e-05, "loss": 0.0884, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12948916852474213, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8079470198675497, "eval_overall_precision": 0.7457212713936431, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3719, "eval_samples_per_second": 502.881, "eval_steps_per_second": 8.068, "step": 7102 }, { "epoch": 68.0, "grad_norm": 0.7333919405937195, "learning_rate": 1.6000000000000003e-05, "loss": 0.0881, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.689655172413793, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5952380952380952, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12930843234062195, "eval_overall_accuracy": 0.9596234827842457, "eval_overall_f1": 0.8052980132450333, "eval_overall_precision": 0.7432762836185819, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3727, "eval_samples_per_second": 501.804, "eval_steps_per_second": 8.05, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.6601905822753906, "learning_rate": 1.55e-05, "loss": 0.0903, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12589633464813232, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8100929614873839, "eval_overall_precision": 0.7493857493857494, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3735, "eval_samples_per_second": 500.62, "eval_steps_per_second": 8.031, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.186720609664917, "learning_rate": 1.5e-05, "loss": 0.089, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.620253164556962, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7352941176470588, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6944444444444444, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.8484848484848486, "eval_TIME_number": 31, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12257770448923111, "eval_overall_accuracy": 0.9628436958137231, "eval_overall_f1": 0.8112449799196787, "eval_overall_precision": 0.7556109725685786, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3731, "eval_samples_per_second": 501.269, "eval_steps_per_second": 8.042, "step": 7420 }, { "epoch": 71.0, "grad_norm": 1.3465250730514526, "learning_rate": 1.45e-05, "loss": 0.0883, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6805555555555556, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5903614457831325, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12590442597866058, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.804780876494024, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3735, "eval_samples_per_second": 500.704, "eval_steps_per_second": 8.033, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.610948085784912, "learning_rate": 1.4000000000000001e-05, "loss": 0.0878, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12648038566112518, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8058510638297872, "eval_overall_precision": 0.7463054187192119, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3794, "eval_samples_per_second": 492.941, "eval_steps_per_second": 7.908, "step": 7632 }, { "epoch": 73.0, "grad_norm": 1.2512165307998657, "learning_rate": 1.3500000000000001e-05, "loss": 0.0866, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8773006134969324, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8265895953757225, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12454748153686523, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8074369189907038, "eval_overall_precision": 0.7469287469287469, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3746, "eval_samples_per_second": 499.258, "eval_steps_per_second": 8.009, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.7970552444458008, "learning_rate": 1.3000000000000001e-05, "loss": 0.0859, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6805555555555556, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.5903614457831325, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8693009118541033, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8125, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.835820895522388, "eval_TIME_number": 31, "eval_TIME_precision": 0.7777777777777778, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12762786448001862, "eval_overall_accuracy": 0.9601189001733961, "eval_overall_f1": 0.8036890645586299, "eval_overall_precision": 0.738498789346247, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3742, "eval_samples_per_second": 499.76, "eval_steps_per_second": 8.018, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.913361132144928, "learning_rate": 1.25e-05, "loss": 0.088, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.742857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6842105263157895, "eval_QUANTITY_recall": 0.8125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12584900856018066, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3743, "eval_samples_per_second": 499.605, "eval_steps_per_second": 8.015, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.470176339149475, "learning_rate": 1.2e-05, "loss": 0.0877, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.7814569536423841, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7195121951219512, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6944444444444445, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6024096385542169, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6857142857142857, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.631578947368421, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12841203808784485, "eval_overall_accuracy": 0.958632648005945, "eval_overall_f1": 0.7994722955145119, "eval_overall_precision": 0.7354368932038835, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3725, "eval_samples_per_second": 502.075, "eval_steps_per_second": 8.055, "step": 8056 }, { "epoch": 77.0, "grad_norm": 1.8821589946746826, "learning_rate": 1.1500000000000002e-05, "loss": 0.0865, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6993006993006993, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8792569659442725, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8352941176470589, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12691272795200348, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3754, "eval_samples_per_second": 498.088, "eval_steps_per_second": 7.991, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.1131901741027832, "learning_rate": 1.1000000000000001e-05, "loss": 0.0873, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12489111721515656, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8021248339973439, "eval_overall_precision": 0.742014742014742, "eval_overall_recall": 0.8728323699421965, "eval_runtime": 0.3728, "eval_samples_per_second": 501.583, "eval_steps_per_second": 8.047, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.7601754069328308, "learning_rate": 1.05e-05, "loss": 0.0837, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8738461538461538, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8255813953488372, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.6956521739130435, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6486486486486487, "eval_QUANTITY_recall": 0.75, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1264895647764206, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.804780876494024, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3752, "eval_samples_per_second": 498.393, "eval_steps_per_second": 7.996, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.6998342871665955, "learning_rate": 1e-05, "loss": 0.0866, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.13076122105121613, "eval_overall_accuracy": 0.9603666088679713, "eval_overall_f1": 0.8090185676392574, "eval_overall_precision": 0.7475490196078431, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3724, "eval_samples_per_second": 502.187, "eval_steps_per_second": 8.056, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.47672829031944275, "learning_rate": 9.5e-06, "loss": 0.084, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12743818759918213, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8074369189907038, "eval_overall_precision": 0.7469287469287469, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3752, "eval_samples_per_second": 498.348, "eval_steps_per_second": 7.995, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.3104524612426758, "learning_rate": 9e-06, "loss": 0.0858, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12744171917438507, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3751, "eval_samples_per_second": 498.519, "eval_steps_per_second": 7.998, "step": 8692 }, { "epoch": 83.0, "grad_norm": 0.5750565528869629, "learning_rate": 8.500000000000002e-06, "loss": 0.0837, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12583325803279877, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3729, "eval_samples_per_second": 501.535, "eval_steps_per_second": 8.046, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.7209677696228027, "learning_rate": 8.000000000000001e-06, "loss": 0.0866, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1269911527633667, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8058510638297872, "eval_overall_precision": 0.7463054187192119, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3722, "eval_samples_per_second": 502.452, "eval_steps_per_second": 8.061, "step": 8904 }, { "epoch": 85.0, "grad_norm": 1.8824012279510498, "learning_rate": 7.5e-06, "loss": 0.0837, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.6901408450704226, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.8032786885245902, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12705950438976288, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8058510638297872, "eval_overall_precision": 0.7463054187192119, "eval_overall_recall": 0.8757225433526011, "eval_runtime": 0.3715, "eval_samples_per_second": 503.358, "eval_steps_per_second": 8.075, "step": 9010 }, { "epoch": 86.0, "grad_norm": 2.3330228328704834, "learning_rate": 7.000000000000001e-06, "loss": 0.085, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.7866666666666667, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7283950617283951, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12910060584545135, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8090185676392574, "eval_overall_precision": 0.7475490196078431, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3729, "eval_samples_per_second": 501.432, "eval_steps_per_second": 8.044, "step": 9116 }, { "epoch": 87.0, "grad_norm": 2.0060434341430664, "learning_rate": 6.5000000000000004e-06, "loss": 0.0818, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8711656441717791, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8208092485549133, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1290162354707718, "eval_overall_accuracy": 0.9606143175625464, "eval_overall_f1": 0.8063660477453581, "eval_overall_precision": 0.7450980392156863, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3722, "eval_samples_per_second": 502.389, "eval_steps_per_second": 8.06, "step": 9222 }, { "epoch": 88.0, "grad_norm": 1.1834133863449097, "learning_rate": 6e-06, "loss": 0.0814, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8765432098765433, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8304093567251462, "eval_PERSON_recall": 0.9281045751633987, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12794728577136993, "eval_overall_accuracy": 0.9611097349516968, "eval_overall_f1": 0.8085106382978724, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8786127167630058, "eval_runtime": 0.3732, "eval_samples_per_second": 501.069, "eval_steps_per_second": 8.039, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.2125024795532227, "learning_rate": 5.500000000000001e-06, "loss": 0.0845, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1287134289741516, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8127490039840638, "eval_overall_precision": 0.7518427518427518, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3745, "eval_samples_per_second": 499.313, "eval_steps_per_second": 8.01, "step": 9434 }, { "epoch": 90.0, "grad_norm": 3.6503348350524902, "learning_rate": 5e-06, "loss": 0.0838, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8854489164086689, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8411764705882353, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12891411781311035, "eval_overall_accuracy": 0.9618528610354223, "eval_overall_f1": 0.8138297872340425, "eval_overall_precision": 0.7536945812807881, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3711, "eval_samples_per_second": 503.843, "eval_steps_per_second": 8.083, "step": 9540 }, { "epoch": 91.0, "grad_norm": 0.752189040184021, "learning_rate": 4.5e-06, "loss": 0.0832, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8854489164086689, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8411764705882353, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12811307609081268, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8138297872340425, "eval_overall_precision": 0.7536945812807881, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.372, "eval_samples_per_second": 502.739, "eval_steps_per_second": 8.065, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.4708694219589233, "learning_rate": 4.000000000000001e-06, "loss": 0.0818, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8854489164086689, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8411764705882353, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12748010456562042, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8122503328894806, "eval_overall_precision": 0.7530864197530864, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3742, "eval_samples_per_second": 499.78, "eval_steps_per_second": 8.018, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.8394293189048767, "learning_rate": 3.5000000000000004e-06, "loss": 0.0843, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6144578313253012, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7142857142857143, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6578947368421053, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12908503413200378, "eval_overall_accuracy": 0.9608620262571216, "eval_overall_f1": 0.8105960264900662, "eval_overall_precision": 0.7481662591687042, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3732, "eval_samples_per_second": 501.076, "eval_steps_per_second": 8.039, "step": 9858 }, { "epoch": 94.0, "grad_norm": 0.8784964084625244, "learning_rate": 3e-06, "loss": 0.0821, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12788699567317963, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3742, "eval_samples_per_second": 499.732, "eval_steps_per_second": 8.017, "step": 9964 }, { "epoch": 95.0, "grad_norm": 1.3944754600524902, "learning_rate": 2.5e-06, "loss": 0.0807, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12791010737419128, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3722, "eval_samples_per_second": 502.394, "eval_steps_per_second": 8.06, "step": 10070 }, { "epoch": 96.0, "grad_norm": 2.0656416416168213, "learning_rate": 2.0000000000000003e-06, "loss": 0.0833, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.7132867132867133, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.8360655737704918, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12910382449626923, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8127490039840638, "eval_overall_precision": 0.7518427518427518, "eval_overall_recall": 0.884393063583815, "eval_runtime": 0.3791, "eval_samples_per_second": 493.238, "eval_steps_per_second": 7.913, "step": 10176 }, { "epoch": 97.0, "grad_norm": 6.939116477966309, "learning_rate": 1.5e-06, "loss": 0.0835, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.1281178891658783, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.376, "eval_samples_per_second": 497.302, "eval_steps_per_second": 7.978, "step": 10282 }, { "epoch": 98.0, "grad_norm": 1.4033215045928955, "learning_rate": 1.0000000000000002e-06, "loss": 0.081, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12827619910240173, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3743, "eval_samples_per_second": 499.639, "eval_steps_per_second": 8.016, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.0604668855667114, "learning_rate": 5.000000000000001e-07, "loss": 0.0815, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8854489164086689, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8411764705882353, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12803325057029724, "eval_overall_accuracy": 0.9616051523408472, "eval_overall_f1": 0.8122503328894806, "eval_overall_precision": 0.7530864197530864, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3701, "eval_samples_per_second": 505.209, "eval_steps_per_second": 8.105, "step": 10494 }, { "epoch": 100.0, "grad_norm": 1.724523901939392, "learning_rate": 0.0, "loss": 0.0848, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.7919463087248322, "eval_LOCATION_number": 69, "eval_LOCATION_precision": 0.7375, "eval_LOCATION_recall": 0.855072463768116, "eval_ORGANIZATION_f1": 0.704225352112676, "eval_ORGANIZATION_number": 61, "eval_ORGANIZATION_precision": 0.6172839506172839, "eval_ORGANIZATION_recall": 0.819672131147541, "eval_PERSON_f1": 0.8827160493827161, "eval_PERSON_number": 153, "eval_PERSON_precision": 0.8362573099415205, "eval_PERSON_recall": 0.934640522875817, "eval_QUANTITY_f1": 0.7246376811594203, "eval_QUANTITY_number": 32, "eval_QUANTITY_precision": 0.6756756756756757, "eval_QUANTITY_recall": 0.78125, "eval_TIME_f1": 0.823529411764706, "eval_TIME_number": 31, "eval_TIME_precision": 0.7567567567567568, "eval_TIME_recall": 0.9032258064516129, "eval_loss": 0.12820416688919067, "eval_overall_accuracy": 0.961357443646272, "eval_overall_f1": 0.8111702127659576, "eval_overall_precision": 0.7512315270935961, "eval_overall_recall": 0.8815028901734104, "eval_runtime": 0.3721, "eval_samples_per_second": 502.522, "eval_steps_per_second": 8.062, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4576320229644174.0, "train_loss": 0.14307242384496724, "train_runtime": 560.7825, "train_samples_per_second": 300.83, "train_steps_per_second": 18.902 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4576320229644174.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }