{ "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": 1.6370744705200195, "learning_rate": 4.9500000000000004e-05, "loss": 1.2587, "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": 0.7307424545288086, "eval_overall_accuracy": 0.8365739601279842, "eval_overall_f1": 0.0, "eval_overall_precision": 0.0, "eval_overall_recall": 0.0, "eval_runtime": 0.3763, "eval_samples_per_second": 496.93, "eval_steps_per_second": 7.972, "step": 106 }, { "epoch": 2.0, "grad_norm": 6.390524864196777, "learning_rate": 4.9e-05, "loss": 0.7063, "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": 0.6230493783950806, "eval_overall_accuracy": 0.8375584543440807, "eval_overall_f1": 0.005586592178770949, "eval_overall_precision": 0.14285714285714285, "eval_overall_recall": 0.002849002849002849, "eval_runtime": 0.373, "eval_samples_per_second": 501.355, "eval_steps_per_second": 8.043, "step": 212 }, { "epoch": 3.0, "grad_norm": 1.1493935585021973, "learning_rate": 4.85e-05, "loss": 0.612, "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": 0.07100591715976332, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.3157894736842105, "eval_PERSON_recall": 0.04, "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": 0.5286092758178711, "eval_overall_accuracy": 0.8437115431946838, "eval_overall_f1": 0.036458333333333336, "eval_overall_precision": 0.21212121212121213, "eval_overall_recall": 0.019943019943019943, "eval_runtime": 0.3703, "eval_samples_per_second": 504.935, "eval_steps_per_second": 8.101, "step": 318 }, { "epoch": 4.0, "grad_norm": 1.3580924272537231, "learning_rate": 4.8e-05, "loss": 0.5187, "step": 424 }, { "epoch": 4.0, "eval_LOCATION_f1": 0.16470588235294117, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5833333333333334, "eval_LOCATION_recall": 0.0958904109589041, "eval_ORGANIZATION_f1": 0.025641025641025644, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.07692307692307693, "eval_ORGANIZATION_recall": 0.015384615384615385, "eval_PERSON_f1": 0.2764227642276423, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.3541666666666667, "eval_PERSON_recall": 0.22666666666666666, "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": 0.42886805534362793, "eval_overall_accuracy": 0.8700467634752646, "eval_overall_f1": 0.2, "eval_overall_precision": 0.35251798561151076, "eval_overall_recall": 0.1396011396011396, "eval_runtime": 0.3714, "eval_samples_per_second": 503.492, "eval_steps_per_second": 8.077, "step": 424 }, { "epoch": 5.0, "grad_norm": 1.2623740434646606, "learning_rate": 4.75e-05, "loss": 0.4206, "step": 530 }, { "epoch": 5.0, "eval_LOCATION_f1": 0.40650406504065034, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5, "eval_LOCATION_recall": 0.3424657534246575, "eval_ORGANIZATION_f1": 0.2692307692307693, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.358974358974359, "eval_ORGANIZATION_recall": 0.2153846153846154, "eval_PERSON_f1": 0.6900958466453674, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.6625766871165644, "eval_PERSON_recall": 0.72, "eval_QUANTITY_f1": 0.05405405405405405, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.125, "eval_QUANTITY_recall": 0.034482758620689655, "eval_TIME_f1": 0.5970149253731343, "eval_TIME_number": 34, "eval_TIME_precision": 0.6060606060606061, "eval_TIME_recall": 0.5882352941176471, "eval_loss": 0.34271273016929626, "eval_overall_accuracy": 0.9094265321191238, "eval_overall_f1": 0.5217391304347827, "eval_overall_precision": 0.5733788395904437, "eval_overall_recall": 0.47863247863247865, "eval_runtime": 0.373, "eval_samples_per_second": 501.316, "eval_steps_per_second": 8.043, "step": 530 }, { "epoch": 6.0, "grad_norm": 1.2327097654342651, "learning_rate": 4.7e-05, "loss": 0.3388, "step": 636 }, { "epoch": 6.0, "eval_LOCATION_f1": 0.567741935483871, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5365853658536586, "eval_LOCATION_recall": 0.6027397260273972, "eval_ORGANIZATION_f1": 0.4122137404580153, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4090909090909091, "eval_ORGANIZATION_recall": 0.4153846153846154, "eval_PERSON_f1": 0.7988165680473374, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7180851063829787, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.3934426229508197, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.375, "eval_QUANTITY_recall": 0.41379310344827586, "eval_TIME_f1": 0.7222222222222222, "eval_TIME_number": 34, "eval_TIME_precision": 0.6842105263157895, "eval_TIME_recall": 0.7647058823529411, "eval_loss": 0.2868286073207855, "eval_overall_accuracy": 0.9271474280088604, "eval_overall_f1": 0.6446499339498019, "eval_overall_precision": 0.6009852216748769, "eval_overall_recall": 0.6951566951566952, "eval_runtime": 0.3765, "eval_samples_per_second": 496.697, "eval_steps_per_second": 7.968, "step": 636 }, { "epoch": 7.0, "grad_norm": 6.483063697814941, "learning_rate": 4.6500000000000005e-05, "loss": 0.2819, "step": 742 }, { "epoch": 7.0, "eval_LOCATION_f1": 0.588957055214724, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5333333333333333, "eval_LOCATION_recall": 0.6575342465753424, "eval_ORGANIZATION_f1": 0.4142857142857143, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.38666666666666666, "eval_ORGANIZATION_recall": 0.4461538461538462, "eval_PERSON_f1": 0.8217522658610271, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7513812154696132, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.43750000000000006, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4, "eval_QUANTITY_recall": 0.4827586206896552, "eval_TIME_f1": 0.7397260273972601, "eval_TIME_number": 34, "eval_TIME_precision": 0.6923076923076923, "eval_TIME_recall": 0.7941176470588235, "eval_loss": 0.2394540160894394, "eval_overall_accuracy": 0.9308392813192222, "eval_overall_f1": 0.6588845654993515, "eval_overall_precision": 0.6047619047619047, "eval_overall_recall": 0.7236467236467237, "eval_runtime": 0.3729, "eval_samples_per_second": 501.505, "eval_steps_per_second": 8.046, "step": 742 }, { "epoch": 8.0, "grad_norm": 1.2606326341629028, "learning_rate": 4.600000000000001e-05, "loss": 0.2487, "step": 848 }, { "epoch": 8.0, "eval_LOCATION_f1": 0.658682634730539, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.5851063829787234, "eval_LOCATION_recall": 0.7534246575342466, "eval_ORGANIZATION_f1": 0.4827586206896552, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4375, "eval_ORGANIZATION_recall": 0.5384615384615384, "eval_PERSON_f1": 0.8292682926829269, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7640449438202247, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.41269841269841273, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.38235294117647056, "eval_QUANTITY_recall": 0.4482758620689655, "eval_TIME_f1": 0.7297297297297296, "eval_TIME_number": 34, "eval_TIME_precision": 0.675, "eval_TIME_recall": 0.7941176470588235, "eval_loss": 0.21583667397499084, "eval_overall_accuracy": 0.9362539995077529, "eval_overall_f1": 0.6846846846846847, "eval_overall_precision": 0.6244131455399061, "eval_overall_recall": 0.7578347578347578, "eval_runtime": 0.3731, "eval_samples_per_second": 501.231, "eval_steps_per_second": 8.041, "step": 848 }, { "epoch": 9.0, "grad_norm": 2.007969856262207, "learning_rate": 4.55e-05, "loss": 0.2255, "step": 954 }, { "epoch": 9.0, "eval_LOCATION_f1": 0.7023809523809524, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6210526315789474, "eval_LOCATION_recall": 0.8082191780821918, "eval_ORGANIZATION_f1": 0.5419354838709677, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4666666666666667, "eval_ORGANIZATION_recall": 0.6461538461538462, "eval_PERSON_f1": 0.8395061728395062, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7816091954022989, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.4262295081967213, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.40625, "eval_QUANTITY_recall": 0.4482758620689655, "eval_TIME_f1": 0.6933333333333332, "eval_TIME_number": 34, "eval_TIME_precision": 0.6341463414634146, "eval_TIME_recall": 0.7647058823529411, "eval_loss": 0.20087261497974396, "eval_overall_accuracy": 0.9374846172778735, "eval_overall_f1": 0.7049808429118773, "eval_overall_precision": 0.6388888888888888, "eval_overall_recall": 0.7863247863247863, "eval_runtime": 0.3737, "eval_samples_per_second": 500.448, "eval_steps_per_second": 8.029, "step": 954 }, { "epoch": 10.0, "grad_norm": 0.8239966630935669, "learning_rate": 4.5e-05, "loss": 0.2062, "step": 1060 }, { "epoch": 10.0, "eval_LOCATION_f1": 0.7393939393939394, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6630434782608695, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.5822784810126582, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4946236559139785, "eval_ORGANIZATION_recall": 0.7076923076923077, "eval_PERSON_f1": 0.8363636363636363, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7666666666666667, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.5245901639344263, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.5517241379310345, "eval_TIME_f1": 0.7567567567567567, "eval_TIME_number": 34, "eval_TIME_precision": 0.7, "eval_TIME_recall": 0.8235294117647058, "eval_loss": 0.1920880824327469, "eval_overall_accuracy": 0.9419148412503077, "eval_overall_f1": 0.7335025380710659, "eval_overall_precision": 0.6613272311212814, "eval_overall_recall": 0.8233618233618234, "eval_runtime": 0.3738, "eval_samples_per_second": 500.32, "eval_steps_per_second": 8.027, "step": 1060 }, { "epoch": 11.0, "grad_norm": 1.5922843217849731, "learning_rate": 4.4500000000000004e-05, "loss": 0.1965, "step": 1166 }, { "epoch": 11.0, "eval_LOCATION_f1": 0.7100591715976331, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.625, "eval_LOCATION_recall": 0.821917808219178, "eval_ORGANIZATION_f1": 0.5889570552147239, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.4897959183673469, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8353658536585366, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7696629213483146, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.5538461538461539, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6206896551724138, "eval_TIME_f1": 0.7272727272727273, "eval_TIME_number": 34, "eval_TIME_precision": 0.6511627906976745, "eval_TIME_recall": 0.8235294117647058, "eval_loss": 0.1852114200592041, "eval_overall_accuracy": 0.9396997292640906, "eval_overall_f1": 0.7256857855361597, "eval_overall_precision": 0.6452328159645233, "eval_overall_recall": 0.8290598290598291, "eval_runtime": 0.3736, "eval_samples_per_second": 500.574, "eval_steps_per_second": 8.031, "step": 1166 }, { "epoch": 12.0, "grad_norm": 1.42921781539917, "learning_rate": 4.4000000000000006e-05, "loss": 0.1818, "step": 1272 }, { "epoch": 12.0, "eval_LOCATION_f1": 0.7529411764705882, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6597938144329897, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.5853658536585367, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.48484848484848486, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8421052631578947, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7861271676300579, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5074626865671642, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.4473684210526316, "eval_QUANTITY_recall": 0.5862068965517241, "eval_TIME_f1": 0.7341772151898734, "eval_TIME_number": 34, "eval_TIME_precision": 0.6444444444444445, "eval_TIME_recall": 0.8529411764705882, "eval_loss": 0.1793593168258667, "eval_overall_accuracy": 0.9419148412503077, "eval_overall_f1": 0.7322540473225404, "eval_overall_precision": 0.6504424778761062, "eval_overall_recall": 0.8376068376068376, "eval_runtime": 0.3724, "eval_samples_per_second": 502.093, "eval_steps_per_second": 8.055, "step": 1272 }, { "epoch": 13.0, "grad_norm": 1.1510792970657349, "learning_rate": 4.35e-05, "loss": 0.1747, "step": 1378 }, { "epoch": 13.0, "eval_LOCATION_f1": 0.7560975609756097, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6813186813186813, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6233766233766234, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5393258426966292, "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": 0.6031746031746031, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5588235294117647, "eval_QUANTITY_recall": 0.6551724137931034, "eval_TIME_f1": 0.767123287671233, "eval_TIME_number": 34, "eval_TIME_precision": 0.717948717948718, "eval_TIME_recall": 0.8235294117647058, "eval_loss": 0.16559341549873352, "eval_overall_accuracy": 0.94683731233079, "eval_overall_f1": 0.7522464698331193, "eval_overall_precision": 0.6845794392523364, "eval_overall_recall": 0.8347578347578347, "eval_runtime": 0.3729, "eval_samples_per_second": 501.412, "eval_steps_per_second": 8.044, "step": 1378 }, { "epoch": 14.0, "grad_norm": 1.169286847114563, "learning_rate": 4.3e-05, "loss": 0.1723, "step": 1484 }, { "epoch": 14.0, "eval_LOCATION_f1": 0.7701863354037267, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7045454545454546, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6012269938650306, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5538461538461539, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6206896551724138, "eval_TIME_f1": 0.717948717948718, "eval_TIME_number": 34, "eval_TIME_precision": 0.6363636363636364, "eval_TIME_recall": 0.8235294117647058, "eval_loss": 0.16448074579238892, "eval_overall_accuracy": 0.9456066945606695, "eval_overall_f1": 0.7445997458703939, "eval_overall_precision": 0.6720183486238532, "eval_overall_recall": 0.8347578347578347, "eval_runtime": 0.3743, "eval_samples_per_second": 499.558, "eval_steps_per_second": 8.014, "step": 1484 }, { "epoch": 15.0, "grad_norm": 1.2472301721572876, "learning_rate": 4.25e-05, "loss": 0.1626, "step": 1590 }, { "epoch": 15.0, "eval_LOCATION_f1": 0.75, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6631578947368421, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5052631578947369, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8473520249221183, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.7953216374269005, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.5671641791044776, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5, "eval_QUANTITY_recall": 0.6551724137931034, "eval_TIME_f1": 0.7692307692307693, "eval_TIME_number": 34, "eval_TIME_precision": 0.6818181818181818, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.16658160090446472, "eval_overall_accuracy": 0.9441299532365247, "eval_overall_f1": 0.7455919395465995, "eval_overall_precision": 0.6681715575620768, "eval_overall_recall": 0.8433048433048433, "eval_runtime": 0.373, "eval_samples_per_second": 501.282, "eval_steps_per_second": 8.042, "step": 1590 }, { "epoch": 16.0, "grad_norm": 1.5230070352554321, "learning_rate": 4.2e-05, "loss": 0.1582, "step": 1696 }, { "epoch": 16.0, "eval_LOCATION_f1": 0.7393939393939394, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6630434782608695, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6274509803921569, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5454545454545454, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8526645768025077, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8047337278106509, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "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": 0.15897247195243835, "eval_overall_accuracy": 0.9473295594388383, "eval_overall_f1": 0.7570332480818415, "eval_overall_precision": 0.6867749419953596, "eval_overall_recall": 0.8433048433048433, "eval_runtime": 0.3746, "eval_samples_per_second": 499.228, "eval_steps_per_second": 8.009, "step": 1696 }, { "epoch": 17.0, "grad_norm": 0.6365993618965149, "learning_rate": 4.15e-05, "loss": 0.1556, "step": 1802 }, { "epoch": 17.0, "eval_LOCATION_f1": 0.7607361963190183, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6888888888888889, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6075949367088608, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5161290322580645, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6268656716417911, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5526315789473685, "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": 0.16090132296085358, "eval_overall_accuracy": 0.9470834358848141, "eval_overall_f1": 0.7557251908396947, "eval_overall_precision": 0.6827586206896552, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.3703, "eval_samples_per_second": 505.047, "eval_steps_per_second": 8.102, "step": 1802 }, { "epoch": 18.0, "grad_norm": 1.4139217138290405, "learning_rate": 4.1e-05, "loss": 0.1521, "step": 1908 }, { "epoch": 18.0, "eval_LOCATION_f1": 0.7701863354037267, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7045454545454546, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6193548387096774, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5333333333333333, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8616352201257862, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8154761904761905, "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": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15284273028373718, "eval_overall_accuracy": 0.9497907949790795, "eval_overall_f1": 0.7696267696267697, "eval_overall_precision": 0.7018779342723005, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3713, "eval_samples_per_second": 503.701, "eval_steps_per_second": 8.081, "step": 1908 }, { "epoch": 19.0, "grad_norm": 0.8368671536445618, "learning_rate": 4.05e-05, "loss": 0.1507, "step": 2014 }, { "epoch": 19.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6289308176100629, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5319148936170213, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8490566037735849, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8035714285714286, "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": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15364685654640198, "eval_overall_accuracy": 0.9490524243170071, "eval_overall_f1": 0.764102564102564, "eval_overall_precision": 0.6946386946386947, "eval_overall_recall": 0.8490028490028491, "eval_runtime": 0.3717, "eval_samples_per_second": 503.112, "eval_steps_per_second": 8.071, "step": 2014 }, { "epoch": 20.0, "grad_norm": 1.1445201635360718, "learning_rate": 4e-05, "loss": 0.1426, "step": 2120 }, { "epoch": 20.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6216216216216216, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5542168674698795, "eval_ORGANIZATION_recall": 0.7076923076923077, "eval_PERSON_f1": 0.8544303797468354, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.5757575757575758, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5135135135135135, "eval_QUANTITY_recall": 0.6551724137931034, "eval_TIME_f1": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14918731153011322, "eval_overall_accuracy": 0.9500369185331036, "eval_overall_f1": 0.7640156453715775, "eval_overall_precision": 0.7043269230769231, "eval_overall_recall": 0.8347578347578347, "eval_runtime": 0.3707, "eval_samples_per_second": 504.495, "eval_steps_per_second": 8.094, "step": 2120 }, { "epoch": 21.0, "grad_norm": 1.6204472780227661, "learning_rate": 3.9500000000000005e-05, "loss": 0.1406, "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": 0.6308724832214766, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5595238095238095, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8454258675078864, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8023952095808383, "eval_PERSON_recall": 0.8933333333333333, "eval_QUANTITY_f1": 0.6060606060606061, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5405405405405406, "eval_QUANTITY_recall": 0.6896551724137931, "eval_TIME_f1": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14743082225322723, "eval_overall_accuracy": 0.9524981540733448, "eval_overall_f1": 0.7682291666666666, "eval_overall_precision": 0.7074340527577938, "eval_overall_recall": 0.8404558404558404, "eval_runtime": 0.3736, "eval_samples_per_second": 500.485, "eval_steps_per_second": 8.029, "step": 2226 }, { "epoch": 22.0, "grad_norm": 1.1964826583862305, "learning_rate": 3.9000000000000006e-05, "loss": 0.1375, "step": 2332 }, { "epoch": 22.0, "eval_LOCATION_f1": 0.7682926829268293, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6923076923076923, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6163522012578616, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5212765957446809, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8500000000000001, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6363636363636365, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5675675675675675, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15313014388084412, "eval_overall_accuracy": 0.9478218065468865, "eval_overall_f1": 0.7633587786259542, "eval_overall_precision": 0.6896551724137931, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3721, "eval_samples_per_second": 502.581, "eval_steps_per_second": 8.063, "step": 2332 }, { "epoch": 23.0, "grad_norm": 1.223521113395691, "learning_rate": 3.85e-05, "loss": 0.1359, "step": 2438 }, { "epoch": 23.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6455696202531646, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5483870967741935, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8580441640378549, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8143712574850299, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6363636363636365, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5675675675675675, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8311688311688312, "eval_TIME_number": 34, "eval_TIME_precision": 0.7441860465116279, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.1469704806804657, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.7783505154639175, "eval_overall_precision": 0.7105882352941176, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3724, "eval_samples_per_second": 502.165, "eval_steps_per_second": 8.056, "step": 2438 }, { "epoch": 24.0, "grad_norm": 1.477795958518982, "learning_rate": 3.8e-05, "loss": 0.1326, "step": 2544 }, { "epoch": 24.0, "eval_LOCATION_f1": 0.7901234567901235, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7191011235955056, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6363636363636364, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.550561797752809, "eval_ORGANIZATION_recall": 0.7538461538461538, "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": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.15083272755146027, "eval_overall_accuracy": 0.9517597834112724, "eval_overall_f1": 0.7803617571059431, "eval_overall_precision": 0.7139479905437353, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3717, "eval_samples_per_second": 503.084, "eval_steps_per_second": 8.071, "step": 2544 }, { "epoch": 25.0, "grad_norm": 1.213571310043335, "learning_rate": 3.7500000000000003e-05, "loss": 0.1278, "step": 2650 }, { "epoch": 25.0, "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": 0.8634920634920634, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1542501598596573, "eval_overall_accuracy": 0.9492985478710313, "eval_overall_f1": 0.7759282970550576, "eval_overall_precision": 0.7046511627906977, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.373, "eval_samples_per_second": 501.402, "eval_steps_per_second": 8.044, "step": 2650 }, { "epoch": 26.0, "grad_norm": 1.678344488143921, "learning_rate": 3.7e-05, "loss": 0.1302, "step": 2756 }, { "epoch": 26.0, "eval_LOCATION_f1": 0.7721518987341772, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7176470588235294, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6040268456375838, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5357142857142857, "eval_ORGANIZATION_recall": 0.6923076923076923, "eval_PERSON_f1": 0.8544303797468354, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8132530120481928, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.8051948051948051, "eval_TIME_number": 34, "eval_TIME_precision": 0.7209302325581395, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14476777613162994, "eval_overall_accuracy": 0.9505291656411519, "eval_overall_f1": 0.7660130718954249, "eval_overall_precision": 0.7077294685990339, "eval_overall_recall": 0.8347578347578347, "eval_runtime": 0.3715, "eval_samples_per_second": 503.403, "eval_steps_per_second": 8.076, "step": 2756 }, { "epoch": 27.0, "grad_norm": 1.0448905229568481, "learning_rate": 3.65e-05, "loss": 0.1266, "step": 2862 }, { "epoch": 27.0, "eval_LOCATION_f1": 0.7672955974842768, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6308724832214766, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5595238095238095, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8726114649681529, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8353658536585366, "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": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14498956501483917, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.7801047120418848, "eval_overall_precision": 0.7215496368038741, "eval_overall_recall": 0.8490028490028491, "eval_runtime": 0.3706, "eval_samples_per_second": 504.535, "eval_steps_per_second": 8.094, "step": 2862 }, { "epoch": 28.0, "grad_norm": 1.1935324668884277, "learning_rate": 3.6e-05, "loss": 0.1244, "step": 2968 }, { "epoch": 28.0, "eval_LOCATION_f1": 0.7607361963190183, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.6888888888888889, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5697674418604651, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8726114649681529, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6567164179104478, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5789473684210527, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14751355350017548, "eval_overall_accuracy": 0.9520059069652966, "eval_overall_f1": 0.7772020725388602, "eval_overall_precision": 0.7125890736342043, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3712, "eval_samples_per_second": 503.765, "eval_steps_per_second": 8.082, "step": 2968 }, { "epoch": 29.0, "grad_norm": 1.6158292293548584, "learning_rate": 3.55e-05, "loss": 0.1223, "step": 3074 }, { "epoch": 29.0, "eval_LOCATION_f1": 0.7852760736196318, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7111111111111111, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6363636363636364, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.550561797752809, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8726114649681529, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8353658536585366, "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": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15049177408218384, "eval_overall_accuracy": 0.950775289195176, "eval_overall_f1": 0.7777777777777778, "eval_overall_precision": 0.7115839243498818, "eval_overall_recall": 0.8575498575498576, "eval_runtime": 0.3729, "eval_samples_per_second": 501.493, "eval_steps_per_second": 8.045, "step": 3074 }, { "epoch": 30.0, "grad_norm": 4.963561534881592, "learning_rate": 3.5e-05, "loss": 0.1216, "step": 3180 }, { "epoch": 30.0, "eval_LOCATION_f1": 0.7721518987341772, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7176470588235294, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6388888888888888, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5822784810126582, "eval_ORGANIZATION_recall": 0.7076923076923077, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.6349206349206349, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5882352941176471, "eval_QUANTITY_recall": 0.6896551724137931, "eval_TIME_f1": 0.8767123287671232, "eval_TIME_number": 34, "eval_TIME_precision": 0.8205128205128205, "eval_TIME_recall": 0.9411764705882353, "eval_loss": 0.14033010601997375, "eval_overall_accuracy": 0.9537287718434654, "eval_overall_f1": 0.7835325365205843, "eval_overall_precision": 0.7338308457711443, "eval_overall_recall": 0.8404558404558404, "eval_runtime": 0.3709, "eval_samples_per_second": 504.137, "eval_steps_per_second": 8.088, "step": 3180 }, { "epoch": 31.0, "grad_norm": 0.5298508405685425, "learning_rate": 3.45e-05, "loss": 0.1197, "step": 3286 }, { "epoch": 31.0, "eval_LOCATION_f1": 0.7672955974842768, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6394557823129251, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.573170731707317, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6875, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6285714285714286, "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": 0.1418294459581375, "eval_overall_accuracy": 0.9534826482894413, "eval_overall_f1": 0.787878787878788, "eval_overall_precision": 0.7328431372549019, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3711, "eval_samples_per_second": 503.888, "eval_steps_per_second": 8.084, "step": 3286 }, { "epoch": 32.0, "grad_norm": 2.2755866050720215, "learning_rate": 3.4000000000000007e-05, "loss": 0.1175, "step": 3392 }, { "epoch": 32.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6535947712418302, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5681818181818182, "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": 0.6666666666666667, "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": 0.14501163363456726, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.7854356306892067, "eval_overall_precision": 0.722488038277512, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3706, "eval_samples_per_second": 504.644, "eval_steps_per_second": 8.096, "step": 3392 }, { "epoch": 33.0, "grad_norm": 1.624603033065796, "learning_rate": 3.35e-05, "loss": 0.1178, "step": 3498 }, { "epoch": 33.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6266666666666667, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5529411764705883, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8634920634920634, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8242424242424242, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.71875, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6571428571428571, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.8157894736842106, "eval_TIME_number": 34, "eval_TIME_precision": 0.7380952380952381, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.14197108149528503, "eval_overall_accuracy": 0.9520059069652966, "eval_overall_f1": 0.7816993464052289, "eval_overall_precision": 0.7222222222222222, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3733, "eval_samples_per_second": 500.895, "eval_steps_per_second": 8.036, "step": 3498 }, { "epoch": 34.0, "grad_norm": 1.45547616481781, "learning_rate": 3.3e-05, "loss": 0.1142, "step": 3604 }, { "epoch": 34.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6351351351351351, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5662650602409639, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8726114649681529, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14198823273181915, "eval_overall_accuracy": 0.9532365247354172, "eval_overall_f1": 0.7837483617300132, "eval_overall_precision": 0.7257281553398058, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3712, "eval_samples_per_second": 503.726, "eval_steps_per_second": 8.081, "step": 3604 }, { "epoch": 35.0, "grad_norm": 1.698808193206787, "learning_rate": 3.2500000000000004e-05, "loss": 0.1159, "step": 3710 }, { "epoch": 35.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.64, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5647058823529412, "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": 0.7058823529411765, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6153846153846154, "eval_QUANTITY_recall": 0.8275862068965517, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14497017860412598, "eval_overall_accuracy": 0.9532365247354172, "eval_overall_f1": 0.7890625, "eval_overall_precision": 0.7266187050359713, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.372, "eval_samples_per_second": 502.715, "eval_steps_per_second": 8.065, "step": 3710 }, { "epoch": 36.0, "grad_norm": 0.9385290741920471, "learning_rate": 3.2000000000000005e-05, "loss": 0.1131, "step": 3816 }, { "epoch": 36.0, "eval_LOCATION_f1": 0.7777777777777778, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7078651685393258, "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": 0.8753993610223643, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8404907975460123, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14353057742118835, "eval_overall_accuracy": 0.9539748953974896, "eval_overall_f1": 0.78748370273794, "eval_overall_precision": 0.7259615384615384, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3701, "eval_samples_per_second": 505.324, "eval_steps_per_second": 8.107, "step": 3816 }, { "epoch": 37.0, "grad_norm": 1.1011046171188354, "learning_rate": 3.15e-05, "loss": 0.113, "step": 3922 }, { "epoch": 37.0, "eval_LOCATION_f1": 0.7701863354037267, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7045454545454546, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.638036809815951, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5306122448979592, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8616352201257862, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8154761904761905, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6470588235294118, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5641025641025641, "eval_QUANTITY_recall": 0.7586206896551724, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.15234865248203278, "eval_overall_accuracy": 0.9492985478710313, "eval_overall_f1": 0.7700127064803051, "eval_overall_precision": 0.694954128440367, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3713, "eval_samples_per_second": 503.679, "eval_steps_per_second": 8.08, "step": 3922 }, { "epoch": 38.0, "grad_norm": 0.7849928736686707, "learning_rate": 3.1e-05, "loss": 0.1122, "step": 4028 }, { "epoch": 38.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6527777777777777, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5949367088607594, "eval_ORGANIZATION_recall": 0.7230769230769231, "eval_PERSON_f1": 0.8643533123028392, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8203592814371258, "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": 0.14123748242855072, "eval_overall_accuracy": 0.9534826482894413, "eval_overall_f1": 0.7831800262812089, "eval_overall_precision": 0.7268292682926829, "eval_overall_recall": 0.8490028490028491, "eval_runtime": 0.3726, "eval_samples_per_second": 501.941, "eval_steps_per_second": 8.053, "step": 4028 }, { "epoch": 39.0, "grad_norm": 3.6088364124298096, "learning_rate": 3.05e-05, "loss": 0.1097, "step": 4134 }, { "epoch": 39.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.641025641025641, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5494505494505495, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8761904761904761, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8363636363636363, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14366811513900757, "eval_overall_accuracy": 0.9532365247354172, "eval_overall_f1": 0.7855297157622738, "eval_overall_precision": 0.7186761229314421, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3719, "eval_samples_per_second": 502.835, "eval_steps_per_second": 8.067, "step": 4134 }, { "epoch": 40.0, "grad_norm": 0.650290846824646, "learning_rate": 3e-05, "loss": 0.1098, "step": 4240 }, { "epoch": 40.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6490066225165563, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5697674418604651, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8726114649681529, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8353658536585366, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14134834706783295, "eval_overall_accuracy": 0.9539748953974896, "eval_overall_f1": 0.7848761408083441, "eval_overall_precision": 0.7235576923076923, "eval_overall_recall": 0.8575498575498576, "eval_runtime": 0.374, "eval_samples_per_second": 500.058, "eval_steps_per_second": 8.022, "step": 4240 }, { "epoch": 41.0, "grad_norm": 1.017473816871643, "learning_rate": 2.95e-05, "loss": 0.1078, "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": 0.6533333333333333, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5764705882352941, "eval_ORGANIZATION_recall": 0.7538461538461538, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14262568950653076, "eval_overall_accuracy": 0.9534826482894413, "eval_overall_f1": 0.7816993464052289, "eval_overall_precision": 0.7222222222222222, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3727, "eval_samples_per_second": 501.78, "eval_steps_per_second": 8.05, "step": 4346 }, { "epoch": 42.0, "grad_norm": 0.8548632264137268, "learning_rate": 2.9e-05, "loss": 0.1095, "step": 4452 }, { "epoch": 42.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6369426751592356, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5434782608695652, "eval_ORGANIZATION_recall": 0.7692307692307693, "eval_PERSON_f1": 0.8626198083067093, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8282208588957055, "eval_PERSON_recall": 0.9, "eval_QUANTITY_f1": 0.6086956521739131, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.525, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1465131938457489, "eval_overall_accuracy": 0.9524981540733448, "eval_overall_f1": 0.7716129032258064, "eval_overall_precision": 0.7051886792452831, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3727, "eval_samples_per_second": 501.757, "eval_steps_per_second": 8.05, "step": 4452 }, { "epoch": 43.0, "grad_norm": 0.9329050183296204, "learning_rate": 2.8499999999999998e-05, "loss": 0.1082, "step": 4558 }, { "epoch": 43.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6530612244897959, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8670886075949367, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8253012048192772, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14095118641853333, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7843137254901961, "eval_overall_precision": 0.7246376811594203, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3721, "eval_samples_per_second": 502.528, "eval_steps_per_second": 8.062, "step": 4558 }, { "epoch": 44.0, "grad_norm": 3.2247750759124756, "learning_rate": 2.8000000000000003e-05, "loss": 0.1065, "step": 4664 }, { "epoch": 44.0, "eval_LOCATION_f1": 0.7924528301886793, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7325581395348837, "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": 0.8607594936708859, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8192771084337349, "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": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13867002725601196, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7837483617300132, "eval_overall_precision": 0.7257281553398058, "eval_overall_recall": 0.8518518518518519, "eval_runtime": 0.3721, "eval_samples_per_second": 502.486, "eval_steps_per_second": 8.061, "step": 4664 }, { "epoch": 45.0, "grad_norm": 3.5815913677215576, "learning_rate": 2.7500000000000004e-05, "loss": 0.1058, "step": 4770 }, { "epoch": 45.0, "eval_LOCATION_f1": 0.8050314465408805, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7441860465116279, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8706624605678233, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8263473053892215, "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": 0.13923799991607666, "eval_overall_accuracy": 0.9554516367216342, "eval_overall_f1": 0.7942332896461337, "eval_overall_precision": 0.7354368932038835, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3704, "eval_samples_per_second": 504.88, "eval_steps_per_second": 8.1, "step": 4770 }, { "epoch": 46.0, "grad_norm": 2.907482624053955, "learning_rate": 2.7000000000000002e-05, "loss": 0.1033, "step": 4876 }, { "epoch": 46.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6530612244897959, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5853658536585366, "eval_ORGANIZATION_recall": 0.7384615384615385, "eval_PERSON_f1": 0.8717948717948718, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8395061728395061, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.65625, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6, "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": 0.1363789588212967, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7857142857142856, "eval_overall_precision": 0.7333333333333333, "eval_overall_recall": 0.8461538461538461, "eval_runtime": 0.3755, "eval_samples_per_second": 497.945, "eval_steps_per_second": 7.988, "step": 4876 }, { "epoch": 47.0, "grad_norm": 1.325737714767456, "learning_rate": 2.6500000000000004e-05, "loss": 0.1057, "step": 4982 }, { "epoch": 47.0, "eval_LOCATION_f1": 0.7875, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7241379310344828, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6533333333333333, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5764705882352941, "eval_ORGANIZATION_recall": 0.7538461538461538, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1410611867904663, "eval_overall_accuracy": 0.9547132660595619, "eval_overall_f1": 0.788036410923277, "eval_overall_precision": 0.7248803827751196, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3717, "eval_samples_per_second": 503.064, "eval_steps_per_second": 8.071, "step": 4982 }, { "epoch": 48.0, "grad_norm": 6.672816753387451, "learning_rate": 2.6000000000000002e-05, "loss": 0.1062, "step": 5088 }, { "epoch": 48.0, "eval_LOCATION_f1": 0.8050314465408805, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7441860465116279, "eval_LOCATION_recall": 0.8767123287671232, "eval_ORGANIZATION_f1": 0.6712328767123288, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6049382716049383, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8769716088328076, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8323353293413174, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14320684969425201, "eval_overall_accuracy": 0.9547132660595619, "eval_overall_f1": 0.7973856209150327, "eval_overall_precision": 0.7367149758454107, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.373, "eval_samples_per_second": 501.285, "eval_steps_per_second": 8.042, "step": 5088 }, { "epoch": 49.0, "grad_norm": 0.6894783973693848, "learning_rate": 2.5500000000000003e-05, "loss": 0.1006, "step": 5194 }, { "epoch": 49.0, "eval_LOCATION_f1": 0.7924528301886793, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7325581395348837, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5975609756097561, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8761904761904761, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8363636363636363, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14069923758506775, "eval_overall_accuracy": 0.9552055131676102, "eval_overall_f1": 0.7926509186351706, "eval_overall_precision": 0.7347931873479319, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3698, "eval_samples_per_second": 505.727, "eval_steps_per_second": 8.113, "step": 5194 }, { "epoch": 50.0, "grad_norm": 1.443442463874817, "learning_rate": 2.5e-05, "loss": 0.1004, "step": 5300 }, { "epoch": 50.0, "eval_LOCATION_f1": 0.8050314465408805, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7441860465116279, "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": 0.879746835443038, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8373493975903614, "eval_PERSON_recall": 0.9266666666666666, "eval_QUANTITY_f1": 0.6363636363636365, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5675675675675675, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14033810794353485, "eval_overall_accuracy": 0.9544671425055378, "eval_overall_f1": 0.7916666666666666, "eval_overall_precision": 0.7290167865707434, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3746, "eval_samples_per_second": 499.192, "eval_steps_per_second": 8.008, "step": 5300 }, { "epoch": 51.0, "grad_norm": 1.2972335815429688, "learning_rate": 2.45e-05, "loss": 0.1004, "step": 5406 }, { "epoch": 51.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6577181208053692, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5833333333333334, "eval_ORGANIZATION_recall": 0.7538461538461538, "eval_PERSON_f1": 0.8734177215189873, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8313253012048193, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6461538461538462, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.5833333333333334, "eval_QUANTITY_recall": 0.7241379310344828, "eval_TIME_f1": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13990922272205353, "eval_overall_accuracy": 0.9544671425055378, "eval_overall_f1": 0.7843137254901961, "eval_overall_precision": 0.7246376811594203, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3718, "eval_samples_per_second": 502.948, "eval_steps_per_second": 8.069, "step": 5406 }, { "epoch": 52.0, "grad_norm": 1.4539422988891602, "learning_rate": 2.4e-05, "loss": 0.1, "step": 5512 }, { "epoch": 52.0, "eval_LOCATION_f1": 0.7924528301886793, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7325581395348837, "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": 0.8734177215189873, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8313253012048193, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14225150644779205, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7900912646675359, "eval_overall_precision": 0.7283653846153846, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3752, "eval_samples_per_second": 498.425, "eval_steps_per_second": 7.996, "step": 5512 }, { "epoch": 53.0, "grad_norm": 1.7125135660171509, "learning_rate": 2.35e-05, "loss": 0.099, "step": 5618 }, { "epoch": 53.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6375000000000001, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5368421052631579, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8303030303030303, "eval_PERSON_recall": 0.9133333333333333, "eval_QUANTITY_f1": 0.6666666666666666, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.575, "eval_QUANTITY_recall": 0.7931034482758621, "eval_TIME_f1": 0.7792207792207793, "eval_TIME_number": 34, "eval_TIME_precision": 0.6976744186046512, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1469447910785675, "eval_overall_accuracy": 0.9524981540733448, "eval_overall_f1": 0.7769230769230769, "eval_overall_precision": 0.7062937062937062, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3719, "eval_samples_per_second": 502.81, "eval_steps_per_second": 8.066, "step": 5618 }, { "epoch": 54.0, "grad_norm": 1.7067456245422363, "learning_rate": 2.3000000000000003e-05, "loss": 0.0966, "step": 5724 }, { "epoch": 54.0, "eval_LOCATION_f1": 0.7672955974842768, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7093023255813954, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6580645161290322, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5666666666666667, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.8662420382165605, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8292682926829268, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "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": 0.1407339721918106, "eval_overall_accuracy": 0.9527442776273689, "eval_overall_f1": 0.7802340702210663, "eval_overall_precision": 0.7177033492822966, "eval_overall_recall": 0.8547008547008547, "eval_runtime": 0.3741, "eval_samples_per_second": 499.806, "eval_steps_per_second": 8.018, "step": 5724 }, { "epoch": 55.0, "grad_norm": 1.2333046197891235, "learning_rate": 2.25e-05, "loss": 0.0993, "step": 5830 }, { "epoch": 55.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6540880503144655, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5531914893617021, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8761904761904761, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8363636363636363, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1426202952861786, "eval_overall_accuracy": 0.9539748953974896, "eval_overall_f1": 0.7845161290322581, "eval_overall_precision": 0.7169811320754716, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3722, "eval_samples_per_second": 502.417, "eval_steps_per_second": 8.06, "step": 5830 }, { "epoch": 56.0, "grad_norm": 2.1034226417541504, "learning_rate": 2.2000000000000003e-05, "loss": 0.0987, "step": 5936 }, { "epoch": 56.0, "eval_LOCATION_f1": 0.7749999999999999, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7126436781609196, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6710526315789473, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5862068965517241, "eval_ORGANIZATION_recall": 0.7846153846153846, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8373493975903614, "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": 0.1402589976787567, "eval_overall_accuracy": 0.9547132660595619, "eval_overall_f1": 0.7916666666666666, "eval_overall_precision": 0.7290167865707434, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3796, "eval_samples_per_second": 492.597, "eval_steps_per_second": 7.903, "step": 5936 }, { "epoch": 57.0, "grad_norm": 0.6643573641777039, "learning_rate": 2.15e-05, "loss": 0.0994, "step": 6042 }, { "epoch": 57.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.65, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5473684210526316, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "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": 0.14331957697868347, "eval_overall_accuracy": 0.9529904011813931, "eval_overall_f1": 0.788586251621271, "eval_overall_precision": 0.7238095238095238, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3723, "eval_samples_per_second": 502.313, "eval_steps_per_second": 8.058, "step": 6042 }, { "epoch": 58.0, "grad_norm": 0.6412150263786316, "learning_rate": 2.1e-05, "loss": 0.0975, "step": 6148 }, { "epoch": 58.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6666666666666666, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.5714285714285714, "eval_ORGANIZATION_recall": 0.8, "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": 0.14041897654533386, "eval_overall_accuracy": 0.9539748953974896, "eval_overall_f1": 0.7926988265971318, "eval_overall_precision": 0.7307692307692307, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3708, "eval_samples_per_second": 504.287, "eval_steps_per_second": 8.09, "step": 6148 }, { "epoch": 59.0, "grad_norm": 1.8468962907791138, "learning_rate": 2.05e-05, "loss": 0.0976, "step": 6254 }, { "epoch": 59.0, "eval_LOCATION_f1": 0.7770700636942677, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.6891891891891891, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6144578313253012, "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": 0.6461538461538462, "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": 0.13591574132442474, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.7994722955145119, "eval_overall_precision": 0.7444717444717445, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3721, "eval_samples_per_second": 502.524, "eval_steps_per_second": 8.062, "step": 6254 }, { "epoch": 60.0, "grad_norm": 1.731353998184204, "learning_rate": 2e-05, "loss": 0.0964, "step": 6360 }, { "epoch": 60.0, "eval_LOCATION_f1": 0.7721518987341772, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7176470588235294, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.697986577181208, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "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": 0.1385490745306015, "eval_overall_accuracy": 0.9556977602756583, "eval_overall_f1": 0.7952755905511811, "eval_overall_precision": 0.7372262773722628, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3703, "eval_samples_per_second": 505.036, "eval_steps_per_second": 8.102, "step": 6360 }, { "epoch": 61.0, "grad_norm": 1.1987533569335938, "learning_rate": 1.9500000000000003e-05, "loss": 0.0954, "step": 6466 }, { "epoch": 61.0, "eval_LOCATION_f1": 0.7770700636942677, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7261904761904762, "eval_LOCATION_recall": 0.8356164383561644, "eval_ORGANIZATION_f1": 0.697986577181208, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6190476190476191, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8717948717948718, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8395061728395061, "eval_PERSON_recall": 0.9066666666666666, "eval_QUANTITY_f1": 0.676923076923077, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6111111111111112, "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": 0.135517880320549, "eval_overall_accuracy": 0.9554516367216342, "eval_overall_f1": 0.7968337730870712, "eval_overall_precision": 0.742014742014742, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.373, "eval_samples_per_second": 501.389, "eval_steps_per_second": 8.044, "step": 6466 }, { "epoch": 62.0, "grad_norm": 4.096658706665039, "learning_rate": 1.9e-05, "loss": 0.0938, "step": 6572 }, { "epoch": 62.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7172413793103448, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8753993610223643, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8404907975460123, "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": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.1392134130001068, "eval_overall_accuracy": 0.9559438838296825, "eval_overall_f1": 0.8015873015873016, "eval_overall_precision": 0.7481481481481481, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3713, "eval_samples_per_second": 503.603, "eval_steps_per_second": 8.079, "step": 6572 }, { "epoch": 63.0, "grad_norm": 3.0589916706085205, "learning_rate": 1.85e-05, "loss": 0.0935, "step": 6678 }, { "epoch": 63.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.6928104575163399, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6022727272727273, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8698412698412699, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8303030303030303, "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": 0.7894736842105262, "eval_TIME_number": 34, "eval_TIME_precision": 0.7142857142857143, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.14185936748981476, "eval_overall_accuracy": 0.9542210189515137, "eval_overall_f1": 0.7937336814621411, "eval_overall_precision": 0.7325301204819277, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3743, "eval_samples_per_second": 499.638, "eval_steps_per_second": 8.016, "step": 6678 }, { "epoch": 64.0, "grad_norm": 1.2135686874389648, "learning_rate": 1.8e-05, "loss": 0.0943, "step": 6784 }, { "epoch": 64.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7172413793103448, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.879746835443038, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8373493975903614, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13513682782649994, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8084544253632759, "eval_overall_precision": 0.7536945812807881, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3734, "eval_samples_per_second": 500.828, "eval_steps_per_second": 8.035, "step": 6784 }, { "epoch": 65.0, "grad_norm": 1.0723731517791748, "learning_rate": 1.75e-05, "loss": 0.093, "step": 6890 }, { "epoch": 65.0, "eval_LOCATION_f1": 0.779874213836478, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7209302325581395, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7210884353741497, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6463414634146342, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "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": 0.137324720621109, "eval_overall_accuracy": 0.9554516367216342, "eval_overall_f1": 0.8026315789473685, "eval_overall_precision": 0.7457212713936431, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.3728, "eval_samples_per_second": 501.578, "eval_steps_per_second": 8.047, "step": 6890 }, { "epoch": 66.0, "grad_norm": 0.8052380084991455, "learning_rate": 1.7000000000000003e-05, "loss": 0.0922, "step": 6996 }, { "epoch": 66.0, "eval_LOCATION_f1": 0.8076923076923077, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7590361445783133, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7074829931972789, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6341463414634146, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8761904761904761, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8363636363636363, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13625451922416687, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8073878627968336, "eval_overall_precision": 0.7518427518427518, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3722, "eval_samples_per_second": 502.355, "eval_steps_per_second": 8.059, "step": 6996 }, { "epoch": 67.0, "grad_norm": 1.3482667207717896, "learning_rate": 1.65e-05, "loss": 0.0912, "step": 7102 }, { "epoch": 67.0, "eval_LOCATION_f1": 0.802547770700637, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.75, "eval_LOCATION_recall": 0.863013698630137, "eval_ORGANIZATION_f1": 0.7210884353741497, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6463414634146342, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8753993610223643, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8404907975460123, "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": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13759839534759521, "eval_overall_accuracy": 0.9556977602756583, "eval_overall_f1": 0.804749340369393, "eval_overall_precision": 0.7493857493857494, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.3726, "eval_samples_per_second": 501.886, "eval_steps_per_second": 8.052, "step": 7102 }, { "epoch": 68.0, "grad_norm": 1.3148181438446045, "learning_rate": 1.6000000000000003e-05, "loss": 0.0908, "step": 7208 }, { "epoch": 68.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7162162162162162, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6385542168674698, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8810289389067525, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8509316770186336, "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": 0.8, "eval_TIME_number": 34, "eval_TIME_precision": 0.7317073170731707, "eval_TIME_recall": 0.8823529411764706, "eval_loss": 0.13887125253677368, "eval_overall_accuracy": 0.9559438838296825, "eval_overall_f1": 0.8031704095112285, "eval_overall_precision": 0.7487684729064039, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3725, "eval_samples_per_second": 501.982, "eval_steps_per_second": 8.053, "step": 7208 }, { "epoch": 69.0, "grad_norm": 1.0154967308044434, "learning_rate": 1.55e-05, "loss": 0.0905, "step": 7314 }, { "epoch": 69.0, "eval_LOCATION_f1": 0.7848101265822783, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7294117647058823, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.726027397260274, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.654320987654321, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.6865671641791046, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6052631578947368, "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": 0.1376219391822815, "eval_overall_accuracy": 0.9564361309377307, "eval_overall_f1": 0.8063241106719368, "eval_overall_precision": 0.75, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3733, "eval_samples_per_second": 500.988, "eval_steps_per_second": 8.037, "step": 7314 }, { "epoch": 70.0, "grad_norm": 1.1361740827560425, "learning_rate": 1.5e-05, "loss": 0.0913, "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": 0.6986301369863014, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6296296296296297, "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": 0.6461538461538462, "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": 0.13397939503192902, "eval_overall_accuracy": 0.9564361309377307, "eval_overall_f1": 0.8015873015873016, "eval_overall_precision": 0.7481481481481481, "eval_overall_recall": 0.8632478632478633, "eval_runtime": 0.3748, "eval_samples_per_second": 498.915, "eval_steps_per_second": 8.004, "step": 7420 }, { "epoch": 71.0, "grad_norm": 2.124069929122925, "learning_rate": 1.45e-05, "loss": 0.0916, "step": 7526 }, { "epoch": 71.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7058823529411765, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6136363636363636, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.696969696969697, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6216216216216216, "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": 0.13961876928806305, "eval_overall_accuracy": 0.9552055131676102, "eval_overall_f1": 0.8062827225130891, "eval_overall_precision": 0.7457627118644068, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3756, "eval_samples_per_second": 497.843, "eval_steps_per_second": 7.987, "step": 7526 }, { "epoch": 72.0, "grad_norm": 0.8449153304100037, "learning_rate": 1.4000000000000001e-05, "loss": 0.0902, "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": 0.726027397260274, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.654320987654321, "eval_ORGANIZATION_recall": 0.8153846153846154, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13548322021961212, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8095238095238095, "eval_overall_precision": 0.7555555555555555, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3739, "eval_samples_per_second": 500.097, "eval_steps_per_second": 8.023, "step": 7632 }, { "epoch": 73.0, "grad_norm": 0.425387978553772, "learning_rate": 1.3500000000000001e-05, "loss": 0.0912, "step": 7738 }, { "epoch": 73.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.726027397260274, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.654320987654321, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1355520486831665, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8095238095238095, "eval_overall_precision": 0.7555555555555555, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3723, "eval_samples_per_second": 502.274, "eval_steps_per_second": 8.058, "step": 7738 }, { "epoch": 74.0, "grad_norm": 1.236484408378601, "learning_rate": 1.3000000000000001e-05, "loss": 0.0892, "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": 0.6901408450704226, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6363636363636364, "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": 0.6461538461538462, "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": 0.13207848370075226, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8053333333333333, "eval_overall_precision": 0.7568922305764411, "eval_overall_recall": 0.8603988603988604, "eval_runtime": 0.3736, "eval_samples_per_second": 500.6, "eval_steps_per_second": 8.031, "step": 7844 }, { "epoch": 75.0, "grad_norm": 0.7426979541778564, "learning_rate": 1.25e-05, "loss": 0.0895, "step": 7950 }, { "epoch": 75.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "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": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.1352306306362152, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.8100929614873837, "eval_overall_precision": 0.7587064676616916, "eval_overall_recall": 0.8689458689458689, "eval_runtime": 0.3733, "eval_samples_per_second": 500.915, "eval_steps_per_second": 8.036, "step": 7950 }, { "epoch": 76.0, "grad_norm": 1.0712276697158813, "learning_rate": 1.2e-05, "loss": 0.0905, "step": 8056 }, { "epoch": 76.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7172413793103448, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "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": 0.13476784527301788, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.8063660477453581, "eval_overall_precision": 0.7543424317617866, "eval_overall_recall": 0.8660968660968661, "eval_runtime": 0.3724, "eval_samples_per_second": 502.104, "eval_steps_per_second": 8.055, "step": 8056 }, { "epoch": 77.0, "grad_norm": 8.184710502624512, "learning_rate": 1.1500000000000002e-05, "loss": 0.0895, "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": 0.7172413793103448, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.65, "eval_ORGANIZATION_recall": 0.8, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13437636196613312, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8127490039840637, "eval_overall_precision": 0.7611940298507462, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3737, "eval_samples_per_second": 500.407, "eval_steps_per_second": 8.028, "step": 8162 }, { "epoch": 78.0, "grad_norm": 1.3736040592193604, "learning_rate": 1.1000000000000001e-05, "loss": 0.0882, "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": 0.726027397260274, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.654320987654321, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13567619025707245, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8143236074270558, "eval_overall_precision": 0.7617866004962779, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3727, "eval_samples_per_second": 501.707, "eval_steps_per_second": 8.049, "step": 8268 }, { "epoch": 79.0, "grad_norm": 0.9239408373832703, "learning_rate": 1.05e-05, "loss": 0.0877, "step": 8374 }, { "epoch": 79.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7320261437908497, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6363636363636364, "eval_ORGANIZATION_recall": 0.8615384615384616, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "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": 0.1406855285167694, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.807843137254902, "eval_overall_precision": 0.7463768115942029, "eval_overall_recall": 0.8803418803418803, "eval_runtime": 0.3738, "eval_samples_per_second": 500.304, "eval_steps_per_second": 8.026, "step": 8374 }, { "epoch": 80.0, "grad_norm": 0.7240285873413086, "learning_rate": 1e-05, "loss": 0.0876, "step": 8480 }, { "epoch": 80.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7297297297297298, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6506024096385542, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13832524418830872, "eval_overall_accuracy": 0.9561900073837066, "eval_overall_f1": 0.8100263852242744, "eval_overall_precision": 0.7542997542997543, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3732, "eval_samples_per_second": 501.071, "eval_steps_per_second": 8.039, "step": 8480 }, { "epoch": 81.0, "grad_norm": 0.5305002331733704, "learning_rate": 9.5e-06, "loss": 0.0865, "step": 8586 }, { "epoch": 81.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13635414838790894, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8158940397350993, "eval_overall_precision": 0.7623762376237624, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.376, "eval_samples_per_second": 497.277, "eval_steps_per_second": 7.978, "step": 8586 }, { "epoch": 82.0, "grad_norm": 1.9057809114456177, "learning_rate": 9e-06, "loss": 0.0882, "step": 8692 }, { "epoch": 82.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7297297297297298, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6506024096385542, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13461817800998688, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8148148148148149, "eval_overall_precision": 0.7604938271604939, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3748, "eval_samples_per_second": 498.989, "eval_steps_per_second": 8.005, "step": 8692 }, { "epoch": 83.0, "grad_norm": 1.2383646965026855, "learning_rate": 8.500000000000002e-06, "loss": 0.0868, "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": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8789808917197452, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8414634146341463, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13708707690238953, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8126649076517152, "eval_overall_precision": 0.7567567567567568, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3728, "eval_samples_per_second": 501.629, "eval_steps_per_second": 8.048, "step": 8798 }, { "epoch": 84.0, "grad_norm": 1.3145028352737427, "learning_rate": 8.000000000000001e-06, "loss": 0.0884, "step": 8904 }, { "epoch": 84.0, "eval_LOCATION_f1": 0.7898089171974523, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7380952380952381, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13608714938163757, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8148148148148149, "eval_overall_precision": 0.7604938271604939, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3781, "eval_samples_per_second": 494.604, "eval_steps_per_second": 7.935, "step": 8904 }, { "epoch": 85.0, "grad_norm": 3.6917648315429688, "learning_rate": 7.5e-06, "loss": 0.088, "step": 9010 }, { "epoch": 85.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13677531480789185, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8121693121693121, "eval_overall_precision": 0.7580246913580246, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3775, "eval_samples_per_second": 495.354, "eval_steps_per_second": 7.947, "step": 9010 }, { "epoch": 86.0, "grad_norm": 0.643048107624054, "learning_rate": 7.000000000000001e-06, "loss": 0.0869, "step": 9116 }, { "epoch": 86.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.726027397260274, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.654320987654321, "eval_ORGANIZATION_recall": 0.8153846153846154, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.1348443627357483, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8132450331125828, "eval_overall_precision": 0.7599009900990099, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3768, "eval_samples_per_second": 496.319, "eval_steps_per_second": 7.962, "step": 9116 }, { "epoch": 87.0, "grad_norm": 0.7794643044471741, "learning_rate": 6.5000000000000004e-06, "loss": 0.0861, "step": 9222 }, { "epoch": 87.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.1349503993988037, "eval_overall_accuracy": 0.9576667487078513, "eval_overall_f1": 0.8158940397350993, "eval_overall_precision": 0.7623762376237624, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3735, "eval_samples_per_second": 500.607, "eval_steps_per_second": 8.031, "step": 9222 }, { "epoch": 88.0, "grad_norm": 0.9696281552314758, "learning_rate": 6e-06, "loss": 0.0853, "step": 9328 }, { "epoch": 88.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.1358775496482849, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8158940397350993, "eval_overall_precision": 0.7623762376237624, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3762, "eval_samples_per_second": 497.14, "eval_steps_per_second": 7.976, "step": 9328 }, { "epoch": 89.0, "grad_norm": 1.8147895336151123, "learning_rate": 5.500000000000001e-06, "loss": 0.0873, "step": 9434 }, { "epoch": 89.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.1357378214597702, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8169761273209548, "eval_overall_precision": 0.7642679900744417, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3747, "eval_samples_per_second": 499.024, "eval_steps_per_second": 8.006, "step": 9434 }, { "epoch": 90.0, "grad_norm": 1.6982191801071167, "learning_rate": 5e-06, "loss": 0.0869, "step": 9540 }, { "epoch": 90.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13445889949798584, "eval_overall_accuracy": 0.9576667487078513, "eval_overall_f1": 0.8169761273209548, "eval_overall_precision": 0.7642679900744417, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3744, "eval_samples_per_second": 499.404, "eval_steps_per_second": 8.012, "step": 9540 }, { "epoch": 91.0, "grad_norm": 1.2758022546768188, "learning_rate": 4.5e-06, "loss": 0.0855, "step": 9646 }, { "epoch": 91.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7248322147651007, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6428571428571429, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13598185777664185, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8137384412153237, "eval_overall_precision": 0.7586206896551724, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3733, "eval_samples_per_second": 500.966, "eval_steps_per_second": 8.037, "step": 9646 }, { "epoch": 92.0, "grad_norm": 1.1231157779693604, "learning_rate": 4.000000000000001e-06, "loss": 0.0863, "step": 9752 }, { "epoch": 92.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7346938775510204, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6585365853658537, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13555923104286194, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8158940397350993, "eval_overall_precision": 0.7623762376237624, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3733, "eval_samples_per_second": 500.907, "eval_steps_per_second": 8.036, "step": 9752 }, { "epoch": 93.0, "grad_norm": 3.048227071762085, "learning_rate": 3.5000000000000004e-06, "loss": 0.0858, "step": 9858 }, { "epoch": 93.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13597699999809265, "eval_overall_accuracy": 0.9571745015998031, "eval_overall_f1": 0.8158940397350993, "eval_overall_precision": 0.7623762376237624, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3756, "eval_samples_per_second": 497.847, "eval_steps_per_second": 7.987, "step": 9858 }, { "epoch": 94.0, "grad_norm": 1.3223367929458618, "learning_rate": 3e-06, "loss": 0.0857, "step": 9964 }, { "epoch": 94.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8846153846153846, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8518518518518519, "eval_PERSON_recall": 0.92, "eval_QUANTITY_f1": 0.7076923076923076, "eval_QUANTITY_number": 29, "eval_QUANTITY_precision": 0.6388888888888888, "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": 0.13530442118644714, "eval_overall_accuracy": 0.9574206251538272, "eval_overall_f1": 0.8169761273209548, "eval_overall_precision": 0.7642679900744417, "eval_overall_recall": 0.8774928774928775, "eval_runtime": 0.3728, "eval_samples_per_second": 501.55, "eval_steps_per_second": 8.046, "step": 9964 }, { "epoch": 95.0, "grad_norm": 2.3395557403564453, "learning_rate": 2.5e-06, "loss": 0.0862, "step": 10070 }, { "epoch": 95.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.1362064629793167, "eval_overall_accuracy": 0.956928378045779, "eval_overall_f1": 0.8132450331125828, "eval_overall_precision": 0.7599009900990099, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3718, "eval_samples_per_second": 502.962, "eval_steps_per_second": 8.069, "step": 10070 }, { "epoch": 96.0, "grad_norm": 1.0705591440200806, "learning_rate": 2.0000000000000003e-06, "loss": 0.0864, "step": 10176 }, { "epoch": 96.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13568849861621857, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8132450331125828, "eval_overall_precision": 0.7599009900990099, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3725, "eval_samples_per_second": 502.042, "eval_steps_per_second": 8.054, "step": 10176 }, { "epoch": 97.0, "grad_norm": 0.9012406468391418, "learning_rate": 1.5e-06, "loss": 0.0849, "step": 10282 }, { "epoch": 97.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.8266666666666665, "eval_TIME_number": 34, "eval_TIME_precision": 0.7560975609756098, "eval_TIME_recall": 0.9117647058823529, "eval_loss": 0.13571688532829285, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8132450331125828, "eval_overall_precision": 0.7599009900990099, "eval_overall_recall": 0.8746438746438746, "eval_runtime": 0.3741, "eval_samples_per_second": 499.84, "eval_steps_per_second": 8.019, "step": 10282 }, { "epoch": 98.0, "grad_norm": 0.9204326868057251, "learning_rate": 1.0000000000000002e-06, "loss": 0.0836, "step": 10388 }, { "epoch": 98.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.13613446056842804, "eval_overall_accuracy": 0.9564361309377307, "eval_overall_f1": 0.8105960264900662, "eval_overall_precision": 0.7574257425742574, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3746, "eval_samples_per_second": 499.155, "eval_steps_per_second": 8.008, "step": 10388 }, { "epoch": 99.0, "grad_norm": 1.0252379179000854, "learning_rate": 5.000000000000001e-07, "loss": 0.0831, "step": 10494 }, { "epoch": 99.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.13595184683799744, "eval_overall_accuracy": 0.9566822544917548, "eval_overall_f1": 0.8105960264900662, "eval_overall_precision": 0.7574257425742574, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3713, "eval_samples_per_second": 503.665, "eval_steps_per_second": 8.08, "step": 10494 }, { "epoch": 100.0, "grad_norm": 1.394977331161499, "learning_rate": 0.0, "loss": 0.085, "step": 10600 }, { "epoch": 100.0, "eval_LOCATION_f1": 0.7948717948717949, "eval_LOCATION_number": 73, "eval_LOCATION_precision": 0.7469879518072289, "eval_LOCATION_recall": 0.8493150684931506, "eval_ORGANIZATION_f1": 0.7397260273972603, "eval_ORGANIZATION_number": 65, "eval_ORGANIZATION_precision": 0.6666666666666666, "eval_ORGANIZATION_recall": 0.8307692307692308, "eval_PERSON_f1": 0.8817891373801918, "eval_PERSON_number": 150, "eval_PERSON_precision": 0.8466257668711656, "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": 0.1360514611005783, "eval_overall_accuracy": 0.9564361309377307, "eval_overall_f1": 0.8105960264900662, "eval_overall_precision": 0.7574257425742574, "eval_overall_recall": 0.8717948717948718, "eval_runtime": 0.3715, "eval_samples_per_second": 503.418, "eval_steps_per_second": 8.076, "step": 10600 }, { "epoch": 100.0, "step": 10600, "total_flos": 4535917761443712.0, "train_loss": 0.14489822162772126, "train_runtime": 603.3251, "train_samples_per_second": 279.783, "train_steps_per_second": 17.569 } ], "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 }