{ "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": 1.4652527570724487, "learning_rate": 4.9500000000000004e-05, "loss": 1.2491, "step": 106 }, { "epoch": 1.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.0, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.0, "eval_PERSON_recall": 0.0, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 34, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.7288655042648315, "eval_overall_accuracy": 0.8365739601279842, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.9333, "eval_samples_per_second": 200.373, "eval_steps_per_second": 3.215, "step": 106 }, { "epoch": 2.0, "grad_norm": 1.179681658744812, "learning_rate": 4.9e-05, "loss": 0.7042, "step": 212 }, { "epoch": 2.0, "eval_LOCATION_f1": 0.0, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.0, "eval_LOCATION_recall": 0.0, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.012820512820512822, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.16666666666666666, "eval_PERSON_recall": 0.006666666666666667, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 34, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.6214632391929626, "eval_overall_accuracy": 0.8375584543440807, "eval_overall_f1": 0.005586592178770949, "eval_overall_precision": 0.14285714285714285, "eval_overall_recall": 0.002849002849002849, "eval_runtime": 0.9735, "eval_samples_per_second": 192.098, "eval_steps_per_second": 3.082, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.2983235120773315, "learning_rate": 4.85e-05, "loss": 0.6157, "step": 318 }, { "epoch": 3.0, "eval_LOCATION_f1": 0.02631578947368421, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.3333333333333333, "eval_LOCATION_recall": 0.0136986301369863, "eval_ORGANIZATION_f1": 0.0, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.0, "eval_ORGANIZATION_recall": 0.0, "eval_PERSON_f1": 0.058823529411764705, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.25, "eval_PERSON_recall": 0.03333333333333333, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.0, "eval_TIME_number": 34, "eval_TIME_precision": 0.0, "eval_TIME_recall": 0.0, "eval_loss": 0.532402515411377, "eval_overall_accuracy": 0.8437115431946838, "eval_overall_f1": 0.03108808290155441, "eval_overall_precision": 0.17142857142857143, "eval_overall_recall": 0.017094017094017096, "eval_runtime": 1.0085, "eval_samples_per_second": 185.432, "eval_steps_per_second": 2.975, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.2393027544021606, "learning_rate": 4.8e-05, "loss": 0.5215, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.16666666666666663, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6363636363636364, "eval_LOCATION_recall": 0.0958904109589041, "eval_ORGANIZATION_f1": 0.025, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.06666666666666667, "eval_ORGANIZATION_recall": 0.015384615384615385, "eval_PERSON_f1": 0.3102040816326531, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.4, "eval_PERSON_recall": 0.25333333333333335, "eval_QUANTITY_f1": 0.0, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.0, "eval_QUANTITY_recall": 0.0, "eval_TIME_f1": 0.2692307692307692, "eval_TIME_number": 34, "eval_TIME_precision": 0.3888888888888889, "eval_TIME_recall": 0.20588235294117646, "eval_loss": 0.4347396790981293, "eval_overall_accuracy": 0.8707851341373369, "eval_overall_f1": 0.2163265306122449, "eval_overall_precision": 0.381294964028777, "eval_overall_recall": 0.150997150997151, "eval_runtime": 0.9853, "eval_samples_per_second": 189.782, "eval_steps_per_second": 3.045, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.3171206712722778, "learning_rate": 4.75e-05, "loss": 0.4311, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.38260869565217387, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5238095238095238, "eval_LOCATION_recall": 0.3013698630136986, "eval_ORGANIZATION_f1": 0.17021276595744683, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.27586206896551724, "eval_ORGANIZATION_recall": 0.12307692307692308, "eval_PERSON_f1": 0.6098360655737705, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.6, "eval_PERSON_recall": 0.62, "eval_QUANTITY_f1": 0.05405405405405405, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.125, "eval_QUANTITY_recall": 0.034482758620689655, "eval_TIME_f1": 0.6268656716417911, "eval_TIME_number": 34, "eval_TIME_precision": 0.6363636363636364, "eval_TIME_recall": 0.6176470588235294, "eval_loss": 0.35183095932006836, "eval_overall_accuracy": 0.9047501845926655, "eval_overall_f1": 0.46925566343042074, "eval_overall_precision": 0.5430711610486891, "eval_overall_recall": 0.4131054131054131, "eval_runtime": 0.951, "eval_samples_per_second": 196.64, "eval_steps_per_second": 3.155, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.2733343839645386, "learning_rate": 4.7e-05, "loss": 0.3468, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.5165562913907286, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5, "eval_LOCATION_recall": 0.5342465753424658, "eval_ORGANIZATION_f1": 0.39062500000000006, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.3968253968253968, "eval_ORGANIZATION_recall": 0.38461538461538464, "eval_PERSON_f1": 0.7823529411764706, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7, "eval_PERSON_recall": 0.8866666666666667, "eval_QUANTITY_f1": 0.39999999999999997, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.3870967741935484, "eval_QUANTITY_recall": 0.41379310344827586, "eval_TIME_f1": 0.6756756756756757, "eval_TIME_number": 34, "eval_TIME_precision": 0.625, "eval_TIME_recall": 0.7352941176470589, "eval_loss": 0.29307425022125244, "eval_overall_accuracy": 0.9237016982525228, "eval_overall_f1": 0.6215139442231076, "eval_overall_precision": 0.582089552238806, "eval_overall_recall": 0.6666666666666666, "eval_runtime": 0.9368, "eval_samples_per_second": 199.617, "eval_steps_per_second": 3.202, "step": 636 }, { "epoch": 7.0, "grad_norm": 1.3349977731704712, "learning_rate": 4.6500000000000005e-05, "loss": 0.2867, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.6296296296296295, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5730337078651685, "eval_LOCATION_recall": 0.6986301369863014, "eval_ORGANIZATION_f1": 0.4444444444444445, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4050632911392405, "eval_ORGANIZATION_recall": 0.49230769230769234, "eval_PERSON_f1": 0.8179104477611939, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7405405405405405, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.43076923076923074, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.3888888888888889, "eval_QUANTITY_recall": 0.4827586206896552, "eval_TIME_f1": 0.7027027027027027, "eval_TIME_number": 34, "eval_TIME_precision": 0.65, "eval_TIME_recall": 0.7647058823529411, "eval_loss": 0.246965229511261, "eval_overall_accuracy": 0.9328082697514152, "eval_overall_f1": 0.6666666666666666, "eval_overall_precision": 0.6060606060606061, "eval_overall_recall": 0.7407407407407407, "eval_runtime": 0.9397, "eval_samples_per_second": 199.001, "eval_steps_per_second": 3.193, "step": 742 }, { "epoch": 8.0, "grad_norm": 1.5047358274459839, "learning_rate": 4.600000000000001e-05, "loss": 0.2534, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.6380368098159509, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5777777777777777, "eval_LOCATION_recall": 0.7123287671232876, "eval_ORGANIZATION_f1": 0.5070422535211268, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4675324675324675, "eval_ORGANIZATION_recall": 0.5538461538461539, "eval_PERSON_f1": 0.8267477203647415, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7597765363128491, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.4444444444444445, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4117647058823529, "eval_QUANTITY_recall": 0.4827586206896552, "eval_TIME_f1": 0.6933333333333332, "eval_TIME_number": 34, "eval_TIME_precision": 0.6341463414634146, "eval_TIME_recall": 0.7647058823529411, "eval_loss": 0.21960192918777466, "eval_overall_accuracy": 0.9355156288456805, "eval_overall_f1": 0.683937823834197, "eval_overall_precision": 0.6270783847980997, "eval_overall_recall": 0.7521367521367521, "eval_runtime": 0.9508, "eval_samples_per_second": 196.67, "eval_steps_per_second": 3.155, "step": 848 }, { "epoch": 9.0, "grad_norm": 2.822505474090576, "learning_rate": 4.55e-05, "loss": 0.225, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7239263803680981, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6555555555555556, "eval_LOCATION_recall": 0.8082191780821918, "eval_ORGANIZATION_f1": 0.5466666666666666, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4823529411764706, "eval_ORGANIZATION_recall": 0.6307692307692307, "eval_PERSON_f1": 0.8379204892966361, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7740112994350282, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.4444444444444445, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4117647058823529, "eval_QUANTITY_recall": 0.4827586206896552, "eval_TIME_f1": 0.7297297297297296, "eval_TIME_number": 34, "eval_TIME_precision": 0.675, "eval_TIME_recall": 0.7941176470588235, "eval_loss": 0.19911912083625793, "eval_overall_accuracy": 0.9404380999261629, "eval_overall_f1": 0.7155727155727156, "eval_overall_precision": 0.6525821596244131, "eval_overall_recall": 0.792022792022792, "eval_runtime": 0.9711, "eval_samples_per_second": 192.571, "eval_steps_per_second": 3.089, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.7733340859413147, "learning_rate": 4.5e-05, "loss": 0.2073, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7361963190184049, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6666666666666666, "eval_LOCATION_recall": 0.821917808219178, "eval_ORGANIZATION_f1": 0.5771812080536913, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5119047619047619, "eval_ORGANIZATION_recall": 0.6615384615384615, "eval_PERSON_f1": 0.834355828220859, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7727272727272727, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.4838709677419355, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.45454545454545453, "eval_QUANTITY_recall": 0.5172413793103449, "eval_TIME_f1": 0.7837837837837837, "eval_TIME_number": 34, "eval_TIME_precision": 0.725, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.18784372508525848, "eval_overall_accuracy": 0.9421609648043318, "eval_overall_f1": 0.7312661498708009, "eval_overall_precision": 0.6690307328605201, "eval_overall_recall": 0.8062678062678063, "eval_runtime": 0.975, "eval_samples_per_second": 191.794, "eval_steps_per_second": 3.077, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.2668209075927734, "learning_rate": 4.4500000000000004e-05, "loss": 0.1928, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.738095238095238, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6526315789473685, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.588235294117647, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5113636363636364, "eval_ORGANIZATION_recall": 0.6923076923076923, "eval_PERSON_f1": 0.8353658536585366, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7696629213483146, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.5074626865671642, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4473684210526316, "eval_QUANTITY_recall": 0.5862068965517241, "eval_TIME_f1": 0.7631578947368423, "eval_TIME_number": 34, "eval_TIME_precision": 0.6904761904761905, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.17933246493339539, "eval_overall_accuracy": 0.94265321191238, "eval_overall_f1": 0.7323232323232324, "eval_overall_precision": 0.6575963718820862, "eval_overall_recall": 0.8262108262108262, "eval_runtime": 0.9501, "eval_samples_per_second": 196.821, "eval_steps_per_second": 3.158, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.7145781517028809, "learning_rate": 4.4000000000000006e-05, "loss": 0.1834, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.738095238095238, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6526315789473685, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6114649681528661, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5217391304347826, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8369230769230769, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7771428571428571, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5373134328358208, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.47368421052631576, "eval_QUANTITY_recall": 0.6206896551724138, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.17776605486869812, "eval_overall_accuracy": 0.9428993354664041, "eval_overall_f1": 0.7414880201765448, "eval_overall_precision": 0.665158371040724, "eval_overall_recall": 0.8376068376068376, "eval_runtime": 0.9578, "eval_samples_per_second": 195.239, "eval_steps_per_second": 3.132, "step": 1272 }, { "epoch": 13.0, "grad_norm": 0.8720563054084778, "learning_rate": 4.35e-05, "loss": 0.172, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7469879518072289, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6666666666666666, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6143790849673202, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5340909090909091, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8421052631578947, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7861271676300579, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5588235294117647, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.48717948717948717, "eval_QUANTITY_recall": 0.6551724137931034, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1679297238588333, "eval_overall_accuracy": 0.9458528181146936, "eval_overall_f1": 0.7480916030534351, "eval_overall_precision": 0.6758620689655173, "eval_overall_recall": 0.8376068376068376, "eval_runtime": 0.9625, "eval_samples_per_second": 194.292, "eval_steps_per_second": 3.117, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.491217851638794, "learning_rate": 4.3e-05, "loss": 0.171, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7654320987654321, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6966292134831461, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6496815286624205, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5543478260869565, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8411214953271027, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7894736842105263, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.5588235294117647, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.48717948717948717, "eval_QUANTITY_recall": 0.6551724137931034, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16589853167533875, "eval_overall_accuracy": 0.9456066945606695, "eval_overall_f1": 0.756687898089172, "eval_overall_precision": 0.684331797235023, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.9481, "eval_samples_per_second": 197.228, "eval_steps_per_second": 3.164, "step": 1484 }, { "epoch": 15.0, "grad_norm": 1.3357112407684326, "learning_rate": 4.25e-05, "loss": 0.1631, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.7411764705882353, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6494845360824743, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6274509803921569, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5454545454545454, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8509316770186336, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7965116279069767, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6268656716417911, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16929781436920166, "eval_overall_accuracy": 0.9451144474526212, "eval_overall_f1": 0.7579214195183777, "eval_overall_precision": 0.682648401826484, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.955, "eval_samples_per_second": 195.82, "eval_steps_per_second": 3.141, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.694993257522583, "learning_rate": 4.2e-05, "loss": 0.1579, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6631578947368421, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6233766233766234, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5393258426966292, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8553459119496856, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8095238095238095, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6086956521739131, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.525, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16372992098331451, "eval_overall_accuracy": 0.9475756829928624, "eval_overall_f1": 0.7573062261753494, "eval_overall_precision": 0.6834862385321101, "eval_overall_recall": 0.8490028490028491, "eval_runtime": 1.042, "eval_samples_per_second": 179.466, "eval_steps_per_second": 2.879, "step": 1696 }, { "epoch": 17.0, "grad_norm": 2.6867129802703857, "learning_rate": 4.15e-05, "loss": 0.1558, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7730061349693251, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6289308176100629, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5319148936170213, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5797101449275363, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6896551724137931, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15953023731708527, "eval_overall_accuracy": 0.9485601772089589, "eval_overall_f1": 0.7588832487309645, "eval_overall_precision": 0.6842105263157895, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.9584, "eval_samples_per_second": 195.113, "eval_steps_per_second": 3.13, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.2975411415100098, "learning_rate": 4.1e-05, "loss": 0.15, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7901234567901235, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7191011235955056, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8544303797468354, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6060606060606061, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5405405405405406, "eval_QUANTITY_recall": 0.6896551724137931, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1525745838880539, "eval_overall_accuracy": 0.950775289195176, "eval_overall_f1": 0.7766233766233767, "eval_overall_precision": 0.7136038186157518, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.9603, "eval_samples_per_second": 194.722, "eval_steps_per_second": 3.124, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.9000276923179626, "learning_rate": 4.05e-05, "loss": 0.1469, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7901234567901235, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7191011235955056, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.638036809815951, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5306122448979592, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8544303797468354, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15378721058368683, "eval_overall_accuracy": 0.9502830420871278, "eval_overall_f1": 0.7739463601532567, "eval_overall_precision": 0.7013888888888888, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9594, "eval_samples_per_second": 194.917, "eval_steps_per_second": 3.127, "step": 2014 }, { "epoch": 20.0, "grad_norm": 1.5783941745758057, "learning_rate": 4e-05, "loss": 0.1429, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6621621621621622, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5903614457831325, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8544303797468354, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6268656716417911, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1472158133983612, "eval_overall_accuracy": 0.9524981540733448, "eval_overall_f1": 0.7780678851174936, "eval_overall_precision": 0.7180722891566265, "eval_overall_recall": 0.8490028490028491, "eval_runtime": 0.9598, "eval_samples_per_second": 194.837, "eval_steps_per_second": 3.126, "step": 2120 }, { "epoch": 21.0, "grad_norm": 2.0488758087158203, "learning_rate": 3.9500000000000005e-05, "loss": 0.1419, "step": 2226 }, { "epoch": 21.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8598726114649682, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.823170731707317, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14743593335151672, "eval_overall_accuracy": 0.9524981540733448, "eval_overall_f1": 0.7802340702210663, "eval_overall_precision": 0.7177033492822966, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.9574, "eval_samples_per_second": 195.324, "eval_steps_per_second": 3.134, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.5187019109725952, "learning_rate": 3.9000000000000006e-05, "loss": 0.1365, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7926829268292682, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.6455696202531646, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5483870967741935, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8860759493670886, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8433734939759037, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7594936708860759, "eval_TIME_number": 34, "eval_TIME_precision": 0.6666666666666666, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15414337813854218, "eval_overall_accuracy": 0.9517597834112724, "eval_overall_f1": 0.788265306122449, "eval_overall_precision": 0.7136258660508084, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.9544, "eval_samples_per_second": 195.93, "eval_steps_per_second": 3.143, "step": 2332 }, { "epoch": 23.0, "grad_norm": 2.007498025894165, "learning_rate": 3.85e-05, "loss": 0.1356, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.7950310559006212, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7272727272727273, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6493506493506495, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5617977528089888, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1455027163028717, "eval_overall_accuracy": 0.9534826482894413, "eval_overall_f1": 0.7859922178988327, "eval_overall_precision": 0.7214285714285714, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9568, "eval_samples_per_second": 195.44, "eval_steps_per_second": 3.135, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.5448315143585205, "learning_rate": 3.8e-05, "loss": 0.1326, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7878787878787878, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7065217391304348, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.6496815286624205, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5543478260869565, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8761904761904761, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8363636363636363, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.676470588235294, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5897435897435898, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15045028924942017, "eval_overall_accuracy": 0.9522520305193207, "eval_overall_f1": 0.7841634738186462, "eval_overall_precision": 0.7106481481481481, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9528, "eval_samples_per_second": 196.256, "eval_steps_per_second": 3.148, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.4791549444198608, "learning_rate": 3.7500000000000003e-05, "loss": 0.13, "step": 2650 }, { "epoch": 25.0, "eval_LOCATION_f1": 0.7926829268292682, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7142857142857143, "eval_LOCATION_recall": 0.8904109589041096, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5697674418604651, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.676470588235294, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5897435897435898, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1473151594400406, "eval_overall_accuracy": 0.9529904011813931, "eval_overall_f1": 0.7870967741935483, "eval_overall_precision": 0.7193396226415094, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9439, "eval_samples_per_second": 198.109, "eval_steps_per_second": 3.178, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.8120989799499512, "learning_rate": 3.7e-05, "loss": 0.1321, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6619718309859155, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8753993610223643, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14089035987854004, "eval_overall_accuracy": 0.9552055131676102, "eval_overall_f1": 0.7941567065073041, "eval_overall_precision": 0.7437810945273632, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.9518, "eval_samples_per_second": 196.471, "eval_steps_per_second": 3.152, "step": 2756 }, { "epoch": 27.0, "grad_norm": 0.6371389031410217, "learning_rate": 3.65e-05, "loss": 0.1272, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6438356164383562, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5802469135802469, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14270104467868805, "eval_overall_accuracy": 0.9547132660595619, "eval_overall_f1": 0.7916120576671035, "eval_overall_precision": 0.7330097087378641, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9626, "eval_samples_per_second": 194.265, "eval_steps_per_second": 3.117, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.3416866064071655, "learning_rate": 3.6e-05, "loss": 0.1278, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6530612244897959, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6268656716417911, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14526282250881195, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.787958115183246, "eval_overall_precision": 0.7288135593220338, "eval_overall_recall": 0.8575498575498576, "eval_runtime": 1.0218, "eval_samples_per_second": 183.002, "eval_steps_per_second": 2.936, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.6158010959625244, "learning_rate": 3.55e-05, "loss": 0.1242, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5795454545454546, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6176470588235294, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5384615384615384, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14530108869075775, "eval_overall_accuracy": 0.9539748953974896, "eval_overall_f1": 0.7844155844155845, "eval_overall_precision": 0.720763723150358, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9579, "eval_samples_per_second": 195.225, "eval_steps_per_second": 3.132, "step": 3074 }, { "epoch": 30.0, "grad_norm": 1.2722007036209106, "learning_rate": 3.5e-05, "loss": 0.1208, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6713286713286714, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6153846153846154, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8782051282051282, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.845679012345679, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6363636363636365, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5675675675675675, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8108108108108107, "eval_TIME_number": 34, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13934831321239471, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.7952127659574469, "eval_overall_precision": 0.7456359102244389, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.9579, "eval_samples_per_second": 195.229, "eval_steps_per_second": 3.132, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.45983773469924927, "learning_rate": 3.45e-05, "loss": 0.1213, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.8050314465408805, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7441860465116279, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6455696202531646, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5483870967741935, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8745980707395499, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.84472049689441, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5641025641025641, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7435897435897436, "eval_TIME_number": 34, "eval_TIME_precision": 0.6590909090909091, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14607404172420502, "eval_overall_accuracy": 0.9532365247354172, "eval_overall_f1": 0.7803617571059431, "eval_overall_precision": 0.7139479905437353, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9648, "eval_samples_per_second": 193.817, "eval_steps_per_second": 3.109, "step": 3286 }, { "epoch": 32.0, "grad_norm": 0.30338501930236816, "learning_rate": 3.4000000000000007e-05, "loss": 0.1181, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.8050314465408805, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7441860465116279, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6623376623376623, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5730337078651685, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6268656716417911, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5526315789473685, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7837837837837837, "eval_TIME_number": 34, "eval_TIME_precision": 0.725, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14169462025165558, "eval_overall_accuracy": 0.9556977602756583, "eval_overall_f1": 0.7911227154046997, "eval_overall_precision": 0.7301204819277108, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9599, "eval_samples_per_second": 194.803, "eval_steps_per_second": 3.125, "step": 3392 }, { "epoch": 33.0, "grad_norm": 1.1467270851135254, "learning_rate": 3.35e-05, "loss": 0.1191, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.8101265822784809, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7529411764705882, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6493506493506495, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5617977528089888, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7631578947368423, "eval_TIME_number": 34, "eval_TIME_precision": 0.6904761904761905, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1409684270620346, "eval_overall_accuracy": 0.9554516367216342, "eval_overall_f1": 0.788036410923277, "eval_overall_precision": 0.7248803827751196, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 1.0374, "eval_samples_per_second": 180.261, "eval_steps_per_second": 2.892, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.4821702241897583, "learning_rate": 3.3e-05, "loss": 0.1156, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.735632183908046, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6577181208053692, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5833333333333334, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5641025641025641, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7733333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7073170731707317, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14082583785057068, "eval_overall_accuracy": 0.9556977602756583, "eval_overall_f1": 0.7905759162303665, "eval_overall_precision": 0.7312348668280871, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9851, "eval_samples_per_second": 189.819, "eval_steps_per_second": 3.045, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.1249200105667114, "learning_rate": 3.2500000000000004e-05, "loss": 0.1159, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.8, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.735632183908046, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6622516556291391, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5813953488372093, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5641025641025641, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7532467532467532, "eval_TIME_number": 34, "eval_TIME_precision": 0.6744186046511628, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14301134645938873, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7896103896103895, "eval_overall_precision": 0.7255369928400954, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.961, "eval_samples_per_second": 194.591, "eval_steps_per_second": 3.122, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.991729736328125, "learning_rate": 3.2000000000000005e-05, "loss": 0.1133, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6577181208053692, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5833333333333334, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8782051282051282, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.845679012345679, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13775944709777832, "eval_overall_accuracy": 0.9559438838296825, "eval_overall_f1": 0.7921052631578948, "eval_overall_precision": 0.7359413202933985, "eval_overall_recall": 0.8575498575498576, "eval_runtime": 0.9576, "eval_samples_per_second": 195.271, "eval_steps_per_second": 3.133, "step": 3816 }, { "epoch": 37.0, "grad_norm": 0.8443315625190735, "learning_rate": 3.15e-05, "loss": 0.1141, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6582278481012658, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5591397849462365, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.888888888888889, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6376811594202898, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.55, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7435897435897436, "eval_TIME_number": 34, "eval_TIME_precision": 0.6590909090909091, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1476057767868042, "eval_overall_accuracy": 0.9529904011813931, "eval_overall_f1": 0.7846153846153847, "eval_overall_precision": 0.7132867132867133, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9555, "eval_samples_per_second": 195.718, "eval_steps_per_second": 3.14, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.8820420503616333, "learning_rate": 3.1e-05, "loss": 0.1131, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6619718309859155, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6103896103896104, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8917197452229298, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8536585365853658, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8108108108108107, "eval_TIME_number": 34, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13637974858283997, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8031914893617021, "eval_overall_precision": 0.7531172069825436, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9776, "eval_samples_per_second": 191.287, "eval_steps_per_second": 3.069, "step": 4028 }, { "epoch": 39.0, "grad_norm": 7.688674449920654, "learning_rate": 3.05e-05, "loss": 0.1107, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.7950310559006212, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7272727272727273, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6624203821656051, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5652173913043478, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.888888888888889, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5641025641025641, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7532467532467532, "eval_TIME_number": 34, "eval_TIME_precision": 0.6744186046511628, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.14455579221248627, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7892030848329049, "eval_overall_precision": 0.7189695550351288, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9611, "eval_samples_per_second": 194.572, "eval_steps_per_second": 3.121, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.7613418698310852, "learning_rate": 3e-05, "loss": 0.1096, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5795454545454546, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7733333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7073170731707317, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1409280002117157, "eval_overall_accuracy": 0.9554516367216342, "eval_overall_f1": 0.7958115183246073, "eval_overall_precision": 0.7360774818401937, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.953, "eval_samples_per_second": 196.217, "eval_steps_per_second": 3.148, "step": 4240 }, { "epoch": 41.0, "grad_norm": 0.5511670112609863, "learning_rate": 2.95e-05, "loss": 0.1076, "step": 4346 }, { "epoch": 41.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6799999999999999, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8945686900958466, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8588957055214724, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7733333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7073170731707317, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.13955771923065186, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8015768725361366, "eval_overall_precision": 0.7439024390243902, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9543, "eval_samples_per_second": 195.951, "eval_steps_per_second": 3.144, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.7491174340248108, "learning_rate": 2.9e-05, "loss": 0.1074, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.675496688741722, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5930232558139535, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6376811594202898, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.55, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14121000468730927, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.7953063885267275, "eval_overall_precision": 0.7331730769230769, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9549, "eval_samples_per_second": 195.829, "eval_steps_per_second": 3.142, "step": 4452 }, { "epoch": 43.0, "grad_norm": 3.582904100418091, "learning_rate": 2.8499999999999998e-05, "loss": 0.1068, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6714285714285715, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8825396825396825, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8424242424242424, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1361449509859085, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.802124833997344, "eval_overall_precision": 0.7512437810945274, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9551, "eval_samples_per_second": 195.788, "eval_steps_per_second": 3.141, "step": 4558 }, { "epoch": 44.0, "grad_norm": 2.657741069793701, "learning_rate": 2.8000000000000003e-05, "loss": 0.1067, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6853146853146853, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6282051282051282, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8493150684931507, "eval_TIME_number": 34, "eval_TIME_precision": 0.7948717948717948, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13337016105651855, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8047808764940239, "eval_overall_precision": 0.753731343283582, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9555, "eval_samples_per_second": 195.712, "eval_steps_per_second": 3.14, "step": 4664 }, { "epoch": 45.0, "grad_norm": 3.083543300628662, "learning_rate": 2.7500000000000004e-05, "loss": 0.1053, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6799999999999999, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8917197452229298, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8536585365853658, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1369679719209671, "eval_overall_accuracy": 0.9579128722618755, "eval_overall_f1": 0.8068331143232589, "eval_overall_precision": 0.748780487804878, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9521, "eval_samples_per_second": 196.405, "eval_steps_per_second": 3.151, "step": 4770 }, { "epoch": 46.0, "grad_norm": 1.343135952949524, "learning_rate": 2.7000000000000002e-05, "loss": 0.1028, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6802721088435374, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6097560975609756, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8945686900958466, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8588957055214724, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8493150684931507, "eval_TIME_number": 34, "eval_TIME_precision": 0.7948717948717948, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13157421350479126, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8154050464807436, "eval_overall_precision": 0.763681592039801, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9587, "eval_samples_per_second": 195.059, "eval_steps_per_second": 3.129, "step": 4876 }, { "epoch": 47.0, "grad_norm": 2.0871903896331787, "learning_rate": 2.6500000000000004e-05, "loss": 0.1061, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6075949367088608, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.888888888888889, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1331242024898529, "eval_overall_accuracy": 0.9581589958158996, "eval_overall_f1": 0.8042328042328044, "eval_overall_precision": 0.7506172839506173, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9613, "eval_samples_per_second": 194.534, "eval_steps_per_second": 3.121, "step": 4982 }, { "epoch": 48.0, "grad_norm": 11.59224796295166, "learning_rate": 2.6000000000000002e-05, "loss": 0.104, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6845637583892618, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6071428571428571, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8917197452229298, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8536585365853658, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13441863656044006, "eval_overall_accuracy": 0.9579128722618755, "eval_overall_f1": 0.8052631578947369, "eval_overall_precision": 0.7481662591687042, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9557, "eval_samples_per_second": 195.663, "eval_steps_per_second": 3.139, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.8353492617607117, "learning_rate": 2.5500000000000003e-05, "loss": 0.1025, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5882352941176471, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13503114879131317, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8010540184453229, "eval_overall_precision": 0.7450980392156863, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.959, "eval_samples_per_second": 194.987, "eval_steps_per_second": 3.128, "step": 5194 }, { "epoch": 50.0, "grad_norm": 1.756870150566101, "learning_rate": 2.5e-05, "loss": 0.1032, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6758620689655173, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6125, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.888888888888889, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13715174794197083, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8010540184453229, "eval_overall_precision": 0.7450980392156863, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9565, "eval_samples_per_second": 195.497, "eval_steps_per_second": 3.136, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.03740656375885, "learning_rate": 2.45e-05, "loss": 0.0993, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.7924528301886793, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7325581395348837, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6442953020134228, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1355990171432495, "eval_overall_accuracy": 0.9556977602756583, "eval_overall_f1": 0.7900262467191601, "eval_overall_precision": 0.732360097323601, "eval_overall_recall": 0.8575498575498576, "eval_runtime": 0.9593, "eval_samples_per_second": 194.924, "eval_steps_per_second": 3.127, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.2626599073410034, "learning_rate": 2.4e-05, "loss": 0.0992, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6906474820143885, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.888888888888889, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8484848484848485, "eval_PERSON_recall": 0.9333333333333333, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13695622980594635, "eval_overall_accuracy": 0.9576667487078513, "eval_overall_f1": 0.803713527851459, "eval_overall_precision": 0.7518610421836228, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9565, "eval_samples_per_second": 195.512, "eval_steps_per_second": 3.137, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.9839859008789062, "learning_rate": 2.35e-05, "loss": 0.0994, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6753246753246754, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5842696629213483, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14013363420963287, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.796875, "eval_overall_precision": 0.7338129496402878, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9547, "eval_samples_per_second": 195.863, "eval_steps_per_second": 3.142, "step": 5618 }, { "epoch": 54.0, "grad_norm": 1.7605901956558228, "learning_rate": 2.3000000000000003e-05, "loss": 0.0993, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5795454545454546, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1363925337791443, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8010471204188482, "eval_overall_precision": 0.7409200968523002, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9561, "eval_samples_per_second": 195.585, "eval_steps_per_second": 3.138, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.1708297729492188, "learning_rate": 2.25e-05, "loss": 0.0971, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.8101265822784809, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7529411764705882, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6322580645161291, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5444444444444444, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14004166424274445, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.7926988265971318, "eval_overall_precision": 0.7307692307692307, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.958, "eval_samples_per_second": 195.201, "eval_steps_per_second": 3.132, "step": 5830 }, { "epoch": 56.0, "grad_norm": 2.4600577354431152, "learning_rate": 2.2000000000000003e-05, "loss": 0.1, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5697674418604651, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1348854899406433, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.7968545216251638, "eval_overall_precision": 0.7378640776699029, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9627, "eval_samples_per_second": 194.255, "eval_steps_per_second": 3.116, "step": 5936 }, { "epoch": 57.0, "grad_norm": 1.6444453001022339, "learning_rate": 2.15e-05, "loss": 0.0987, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.7924528301886793, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7325581395348837, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6712328767123288, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1363009363412857, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.7984189723320159, "eval_overall_precision": 0.7426470588235294, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9591, "eval_samples_per_second": 194.968, "eval_steps_per_second": 3.128, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.6375830173492432, "learning_rate": 2.1e-05, "loss": 0.0976, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6714285714285715, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6266666666666667, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1327548623085022, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8074866310160427, "eval_overall_precision": 0.760705289672544, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9623, "eval_samples_per_second": 194.331, "eval_steps_per_second": 3.118, "step": 6148 }, { "epoch": 59.0, "grad_norm": 2.3580222129821777, "learning_rate": 2.05e-05, "loss": 0.0957, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6666666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.618421052631579, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.132992684841156, "eval_overall_accuracy": 0.9576667487078513, "eval_overall_f1": 0.8, "eval_overall_precision": 0.7518796992481203, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.9558, "eval_samples_per_second": 195.648, "eval_steps_per_second": 3.139, "step": 6254 }, { "epoch": 60.0, "grad_norm": 1.589872121810913, "learning_rate": 2e-05, "loss": 0.0953, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6799999999999999, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13459840416908264, "eval_overall_accuracy": 0.9581589958158996, "eval_overall_f1": 0.8073878627968336, "eval_overall_precision": 0.7518427518427518, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9605, "eval_samples_per_second": 194.682, "eval_steps_per_second": 3.123, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.7457832098007202, "learning_rate": 1.9500000000000003e-05, "loss": 0.0961, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8533333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7804878048780488, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1298547387123108, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8170894526034712, "eval_overall_precision": 0.7688442211055276, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9648, "eval_samples_per_second": 193.828, "eval_steps_per_second": 3.11, "step": 6466 }, { "epoch": 62.0, "grad_norm": 1.4289331436157227, "learning_rate": 1.9e-05, "loss": 0.0951, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6455696202531646, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13753055036067963, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.7994722955145119, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.9627, "eval_samples_per_second": 194.239, "eval_steps_per_second": 3.116, "step": 6572 }, { "epoch": 63.0, "grad_norm": 5.174590587615967, "learning_rate": 1.85e-05, "loss": 0.0935, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6938775510204082, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6219512195121951, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8853503184713376, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8475609756097561, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8533333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7804878048780488, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1345466524362564, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8089591567852439, "eval_overall_precision": 0.7524509803921569, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9663, "eval_samples_per_second": 193.531, "eval_steps_per_second": 3.105, "step": 6678 }, { "epoch": 64.0, "grad_norm": 1.1309547424316406, "learning_rate": 1.8e-05, "loss": 0.0932, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.8104575163398693, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.775, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6857142857142857, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.64, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8533333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7804878048780488, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13020634651184082, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8096514745308312, "eval_overall_precision": 0.7645569620253164, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.9602, "eval_samples_per_second": 194.76, "eval_steps_per_second": 3.124, "step": 6784 }, { "epoch": 65.0, "grad_norm": 1.1441256999969482, "learning_rate": 1.75e-05, "loss": 0.0941, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 34, "eval_TIME_precision": 0.7619047619047619, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1337554007768631, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8127490039840637, "eval_overall_precision": 0.7611940298507462, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9524, "eval_samples_per_second": 196.337, "eval_steps_per_second": 3.15, "step": 6890 }, { "epoch": 66.0, "grad_norm": 1.6348956823349, "learning_rate": 1.7000000000000003e-05, "loss": 0.0909, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.697986577181208, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.888178913738019, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.852760736196319, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1356654316186905, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8068331143232589, "eval_overall_precision": 0.748780487804878, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9599, "eval_samples_per_second": 194.806, "eval_steps_per_second": 3.125, "step": 6996 }, { "epoch": 67.0, "grad_norm": 1.053985595703125, "learning_rate": 1.65e-05, "loss": 0.0912, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7123287671232877, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6419753086419753, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 34, "eval_TIME_precision": 0.7619047619047619, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13525572419166565, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8153034300791556, "eval_overall_precision": 0.7592137592137592, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.97, "eval_samples_per_second": 192.79, "eval_steps_per_second": 3.093, "step": 7102 }, { "epoch": 68.0, "grad_norm": 1.5947766304016113, "learning_rate": 1.6000000000000003e-05, "loss": 0.0903, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7770700636942677, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7234042553191491, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6710526315789473, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.896774193548387, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.86875, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8421052631578947, "eval_TIME_number": 34, "eval_TIME_precision": 0.7619047619047619, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13356442749500275, "eval_overall_accuracy": 0.9576667487078513, "eval_overall_f1": 0.8133333333333332, "eval_overall_precision": 0.7644110275689223, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9656, "eval_samples_per_second": 193.666, "eval_steps_per_second": 3.107, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.0522669553756714, "learning_rate": 1.55e-05, "loss": 0.0912, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.8129032258064516, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7682926829268293, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6933333333333334, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.611764705882353, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13284043967723846, "eval_overall_accuracy": 0.9579128722618755, "eval_overall_f1": 0.8174603174603174, "eval_overall_precision": 0.762962962962963, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.9644, "eval_samples_per_second": 193.907, "eval_steps_per_second": 3.111, "step": 7314 }, { "epoch": 70.0, "grad_norm": 0.6589028835296631, "learning_rate": 1.5e-05, "loss": 0.0902, "step": 7420 }, { "epoch": 70.0, "eval_LOCATION_f1": 0.7999999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7560975609756098, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6950354609929077, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6447368421052632, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13150876760482788, "eval_overall_accuracy": 0.9581589958158996, "eval_overall_f1": 0.8165997322623829, "eval_overall_precision": 0.7702020202020202, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9609, "eval_samples_per_second": 194.607, "eval_steps_per_second": 3.122, "step": 7420 }, { "epoch": 71.0, "grad_norm": 1.6209025382995605, "learning_rate": 1.45e-05, "loss": 0.0908, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7074829931972789, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6341463414634146, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13572926819324493, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8063241106719368, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9565, "eval_samples_per_second": 195.501, "eval_steps_per_second": 3.136, "step": 7526 }, { "epoch": 72.0, "grad_norm": 1.03559410572052, "learning_rate": 1.4000000000000001e-05, "loss": 0.0897, "step": 7632 }, { "epoch": 72.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8533333333333334, "eval_TIME_number": 34, "eval_TIME_precision": 0.7804878048780488, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13340426981449127, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8106666666666666, "eval_overall_precision": 0.7619047619047619, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9726, "eval_samples_per_second": 192.276, "eval_steps_per_second": 3.085, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.4955795407295227, "learning_rate": 1.3500000000000001e-05, "loss": 0.0896, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7034482758620688, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6375, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1333453506231308, "eval_overall_accuracy": 0.9581589958158996, "eval_overall_f1": 0.8143236074270558, "eval_overall_precision": 0.7617866004962779, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9636, "eval_samples_per_second": 194.067, "eval_steps_per_second": 3.113, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.707966685295105, "learning_rate": 1.3000000000000001e-05, "loss": 0.0882, "step": 7844 }, { "epoch": 74.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6906474820143885, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6486486486486487, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1297333836555481, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8150134048257373, "eval_overall_precision": 0.769620253164557, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9528, "eval_samples_per_second": 196.262, "eval_steps_per_second": 3.149, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.7755259275436401, "learning_rate": 1.25e-05, "loss": 0.0895, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13311755657196045, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8186666666666667, "eval_overall_precision": 0.7694235588972431, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9564, "eval_samples_per_second": 195.535, "eval_steps_per_second": 3.137, "step": 7950 }, { "epoch": 76.0, "grad_norm": 4.219042778015137, "learning_rate": 1.2e-05, "loss": 0.0888, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.7922077922077922, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7530864197530864, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7083333333333334, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6455696202531646, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1329285353422165, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8128342245989305, "eval_overall_precision": 0.7657430730478589, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9598, "eval_samples_per_second": 194.825, "eval_steps_per_second": 3.126, "step": 8056 }, { "epoch": 77.0, "grad_norm": 2.975076675415039, "learning_rate": 1.1500000000000002e-05, "loss": 0.0879, "step": 8162 }, { "epoch": 77.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13204999268054962, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8155080213903743, "eval_overall_precision": 0.7682619647355163, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 1.0462, "eval_samples_per_second": 178.743, "eval_steps_per_second": 2.868, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.8520476818084717, "learning_rate": 1.1000000000000001e-05, "loss": 0.0869, "step": 8268 }, { "epoch": 78.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7042253521126761, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6493506493506493, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13332289457321167, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8117489986648865, "eval_overall_precision": 0.7638190954773869, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.958, "eval_samples_per_second": 195.208, "eval_steps_per_second": 3.132, "step": 8268 }, { "epoch": 79.0, "grad_norm": 1.4421206712722778, "learning_rate": 1.05e-05, "loss": 0.0901, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7974683544303799, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7411764705882353, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7297297297297298, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6506024096385542, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8910256410256411, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8580246913580247, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1383257359266281, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8131578947368421, "eval_overall_precision": 0.7555012224938875, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.9652, "eval_samples_per_second": 193.746, "eval_steps_per_second": 3.108, "step": 8374 }, { "epoch": 80.0, "grad_norm": 1.3702669143676758, "learning_rate": 1e-05, "loss": 0.0871, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7323943661971831, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6753246753246753, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13473859429359436, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.8160000000000001, "eval_overall_precision": 0.7669172932330827, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9538, "eval_samples_per_second": 196.051, "eval_steps_per_second": 3.145, "step": 8480 }, { "epoch": 81.0, "grad_norm": 2.0529441833496094, "learning_rate": 9.5e-06, "loss": 0.0851, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7323943661971831, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6753246753246753, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13238033652305603, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8197596795727637, "eval_overall_precision": 0.7713567839195979, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9602, "eval_samples_per_second": 194.754, "eval_steps_per_second": 3.124, "step": 8586 }, { "epoch": 82.0, "grad_norm": 2.319127321243286, "learning_rate": 9e-06, "loss": 0.0861, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7323943661971831, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6753246753246753, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13330510258674622, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8197596795727637, "eval_overall_precision": 0.7713567839195979, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 1.0386, "eval_samples_per_second": 180.057, "eval_steps_per_second": 2.889, "step": 8692 }, { "epoch": 83.0, "grad_norm": 1.1554148197174072, "learning_rate": 8.500000000000002e-06, "loss": 0.0877, "step": 8798 }, { "epoch": 83.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7412587412587412, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6794871794871795, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8493150684931507, "eval_TIME_number": 34, "eval_TIME_precision": 0.7948717948717948, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1339869350194931, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8197596795727637, "eval_overall_precision": 0.7713567839195979, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9521, "eval_samples_per_second": 196.415, "eval_steps_per_second": 3.151, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.0138518810272217, "learning_rate": 8.000000000000001e-06, "loss": 0.0873, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13319392502307892, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8197596795727637, "eval_overall_precision": 0.7713567839195979, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9541, "eval_samples_per_second": 196.006, "eval_steps_per_second": 3.144, "step": 8904 }, { "epoch": 85.0, "grad_norm": 1.4809114933013916, "learning_rate": 7.5e-06, "loss": 0.0878, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7412587412587412, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6794871794871795, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6666666666666667, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5945945945945946, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8108108108108107, "eval_TIME_number": 34, "eval_TIME_precision": 0.75, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13555191457271576, "eval_overall_accuracy": 0.9581589958158996, "eval_overall_f1": 0.8138297872340426, "eval_overall_precision": 0.7630922693266833, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9587, "eval_samples_per_second": 195.046, "eval_steps_per_second": 3.129, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.6918728947639465, "learning_rate": 7.000000000000001e-06, "loss": 0.0854, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13175515830516815, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8192771084337349, "eval_overall_precision": 0.7727272727272727, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9509, "eval_samples_per_second": 196.659, "eval_steps_per_second": 3.155, "step": 9116 }, { "epoch": 87.0, "grad_norm": 1.3241691589355469, "learning_rate": 6.5000000000000004e-06, "loss": 0.0848, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8648648648648648, "eval_TIME_number": 34, "eval_TIME_precision": 0.8, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.13328462839126587, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8186666666666667, "eval_overall_precision": 0.7694235588972431, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.9604, "eval_samples_per_second": 194.71, "eval_steps_per_second": 3.124, "step": 9222 }, { "epoch": 88.0, "grad_norm": 1.2514363527297974, "learning_rate": 6e-06, "loss": 0.0841, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1320430040359497, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.814419225634179, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9664, "eval_samples_per_second": 193.506, "eval_steps_per_second": 3.104, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.3548272848129272, "learning_rate": 5.500000000000001e-06, "loss": 0.0868, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13209053874015808, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.814419225634179, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9587, "eval_samples_per_second": 195.062, "eval_steps_per_second": 3.129, "step": 9434 }, { "epoch": 90.0, "grad_norm": 2.0916614532470703, "learning_rate": 5e-06, "loss": 0.0844, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13177448511123657, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8128342245989305, "eval_overall_precision": 0.7657430730478589, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 1.0153, "eval_samples_per_second": 184.182, "eval_steps_per_second": 2.955, "step": 9540 }, { "epoch": 91.0, "grad_norm": 2.0040924549102783, "learning_rate": 4.5e-06, "loss": 0.0838, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13262386620044708, "eval_overall_accuracy": 0.9591434900319961, "eval_overall_f1": 0.8160000000000001, "eval_overall_precision": 0.7669172932330827, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9604, "eval_samples_per_second": 194.708, "eval_steps_per_second": 3.124, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.6822946071624756, "learning_rate": 4.000000000000001e-06, "loss": 0.0866, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.133206307888031, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8160000000000001, "eval_overall_precision": 0.7669172932330827, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.9555, "eval_samples_per_second": 195.706, "eval_steps_per_second": 3.14, "step": 9752 }, { "epoch": 93.0, "grad_norm": 0.4100649654865265, "learning_rate": 3.5000000000000004e-06, "loss": 0.085, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1316729038953781, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.8139223560910307, "eval_overall_precision": 0.7676767676767676, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9566, "eval_samples_per_second": 195.484, "eval_steps_per_second": 3.136, "step": 9858 }, { "epoch": 94.0, "grad_norm": 4.882697582244873, "learning_rate": 3e-06, "loss": 0.084, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1321730613708496, "eval_overall_accuracy": 0.958897366477972, "eval_overall_f1": 0.814419225634179, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9581, "eval_samples_per_second": 195.183, "eval_steps_per_second": 3.131, "step": 9964 }, { "epoch": 95.0, "grad_norm": 1.8372896909713745, "learning_rate": 2.5e-06, "loss": 0.0838, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13190868496894836, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.814419225634179, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.9655, "eval_samples_per_second": 193.678, "eval_steps_per_second": 3.107, "step": 10070 }, { "epoch": 96.0, "grad_norm": 1.2674877643585205, "learning_rate": 2.0000000000000003e-06, "loss": 0.087, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7272727272727272, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13277865946292877, "eval_overall_accuracy": 0.9584051193699237, "eval_overall_f1": 0.814419225634179, "eval_overall_precision": 0.7663316582914573, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 1.1022, "eval_samples_per_second": 169.654, "eval_steps_per_second": 2.722, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.8085970878601074, "learning_rate": 1.5e-06, "loss": 0.0832, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.131379634141922, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8139223560910307, "eval_overall_precision": 0.7676767676767676, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9613, "eval_samples_per_second": 194.531, "eval_steps_per_second": 3.121, "step": 10282 }, { "epoch": 98.0, "grad_norm": 1.0001689195632935, "learning_rate": 1.0000000000000002e-06, "loss": 0.0859, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.7870967741935484, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7439024390243902, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13154591619968414, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8139223560910307, "eval_overall_precision": 0.7676767676767676, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9546, "eval_samples_per_second": 195.886, "eval_steps_per_second": 3.143, "step": 10388 }, { "epoch": 99.0, "grad_norm": 0.9420944452285767, "learning_rate": 5.000000000000001e-07, "loss": 0.0838, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13177190721035004, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8128342245989305, "eval_overall_precision": 0.7657430730478589, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9644, "eval_samples_per_second": 193.898, "eval_steps_per_second": 3.111, "step": 10494 }, { "epoch": 100.0, "grad_norm": 0.9724701046943665, "learning_rate": 0.0, "loss": 0.0849, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.7820512820512822, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7349397590361446, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.7183098591549296, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6623376623376623, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8938906752411575, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8633540372670807, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.8378378378378379, "eval_TIME_number": 34, "eval_TIME_precision": 0.775, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1317785680294037, "eval_overall_accuracy": 0.9586512429239479, "eval_overall_f1": 0.8128342245989305, "eval_overall_precision": 0.7657430730478589, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.9669, "eval_samples_per_second": 193.4, "eval_steps_per_second": 3.103, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4535917761443712.0, "train_loss": 0.1449212483639987, "train_runtime": 1228.7031, "train_samples_per_second": 137.381, "train_steps_per_second": 8.627 } ], "logging_steps": 500, "max_steps": 10600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "total_flos": 4535917761443712.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }