nerui-pt-pl20-4 / trainer_state.json
apwic's picture
End of training
3563819 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"eval_steps": 500,
"global_step": 9600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.2417042255401611,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.86,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.2162162162162162,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.256,
"eval_ORGANIZATION_recall": 0.1871345029239766,
"eval_PERSON_f1": 0.3190661478599222,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.3253968253968254,
"eval_PERSON_recall": 0.31297709923664124,
"eval_loss": 0.4039977192878723,
"eval_overall_accuracy": 0.8619165976249655,
"eval_overall_f1": 0.2225609756097561,
"eval_overall_precision": 0.2908366533864542,
"eval_overall_recall": 0.18024691358024691,
"eval_runtime": 0.287,
"eval_samples_per_second": 592.296,
"eval_steps_per_second": 10.452,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.8221556544303894,
"learning_rate": 4.9e-05,
"loss": 0.3784,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.31527093596059114,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.32,
"eval_LOCATION_recall": 0.3106796116504854,
"eval_ORGANIZATION_f1": 0.467065868263473,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.4785276073619632,
"eval_ORGANIZATION_recall": 0.45614035087719296,
"eval_PERSON_f1": 0.4895522388059702,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.4019607843137255,
"eval_PERSON_recall": 0.6259541984732825,
"eval_loss": 0.26177430152893066,
"eval_overall_accuracy": 0.9099696216514775,
"eval_overall_f1": 0.4403669724770642,
"eval_overall_precision": 0.41113490364025695,
"eval_overall_recall": 0.4740740740740741,
"eval_runtime": 0.2879,
"eval_samples_per_second": 590.441,
"eval_steps_per_second": 10.42,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.8273484706878662,
"learning_rate": 4.85e-05,
"loss": 0.2322,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7326732673267327,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.7474747474747475,
"eval_LOCATION_recall": 0.7184466019417476,
"eval_ORGANIZATION_f1": 0.7368421052631577,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.7,
"eval_ORGANIZATION_recall": 0.7777777777777778,
"eval_PERSON_f1": 0.9446494464944649,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9142857142857143,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.12410888820886612,
"eval_overall_accuracy": 0.9632698149682408,
"eval_overall_f1": 0.8033573141486811,
"eval_overall_precision": 0.7808857808857809,
"eval_overall_recall": 0.8271604938271605,
"eval_runtime": 0.2883,
"eval_samples_per_second": 589.572,
"eval_steps_per_second": 10.404,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.1333633661270142,
"learning_rate": 4.8e-05,
"loss": 0.146,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8341232227488151,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8148148148148148,
"eval_LOCATION_recall": 0.8543689320388349,
"eval_ORGANIZATION_f1": 0.8287292817679557,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.7853403141361257,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.0837172195315361,
"eval_overall_accuracy": 0.9748688207677437,
"eval_overall_f1": 0.8745519713261649,
"eval_overall_precision": 0.8472222222222222,
"eval_overall_recall": 0.9037037037037037,
"eval_runtime": 0.2884,
"eval_samples_per_second": 589.37,
"eval_steps_per_second": 10.401,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.40794476866722107,
"learning_rate": 4.75e-05,
"loss": 0.1174,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.9029126213592235,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9029126213592233,
"eval_LOCATION_recall": 0.9029126213592233,
"eval_ORGANIZATION_f1": 0.8670520231213873,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8571428571428571,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.962406015037594,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9481481481481482,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.07148595154285431,
"eval_overall_accuracy": 0.9795636564484949,
"eval_overall_f1": 0.9070904645476773,
"eval_overall_precision": 0.8983050847457628,
"eval_overall_recall": 0.9160493827160494,
"eval_runtime": 0.2882,
"eval_samples_per_second": 589.965,
"eval_steps_per_second": 10.411,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.7415238618850708,
"learning_rate": 4.7e-05,
"loss": 0.1001,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8940092165898617,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8508771929824561,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.851963746223565,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.88125,
"eval_ORGANIZATION_recall": 0.8245614035087719,
"eval_PERSON_f1": 0.9772727272727273,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9699248120300752,
"eval_PERSON_recall": 0.9847328244274809,
"eval_loss": 0.06104715168476105,
"eval_overall_accuracy": 0.9814968240817453,
"eval_overall_f1": 0.9039408866995073,
"eval_overall_precision": 0.9017199017199017,
"eval_overall_recall": 0.9061728395061729,
"eval_runtime": 0.2875,
"eval_samples_per_second": 591.327,
"eval_steps_per_second": 10.435,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.8113571405410767,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0895,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9368421052631579,
"eval_LOCATION_recall": 0.8640776699029126,
"eval_ORGANIZATION_f1": 0.8563380281690139,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8260869565217391,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9809885931558935,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9772727272727273,
"eval_PERSON_recall": 0.9847328244274809,
"eval_loss": 0.05430728569626808,
"eval_overall_accuracy": 0.983706158519746,
"eval_overall_f1": 0.9068627450980392,
"eval_overall_precision": 0.9002433090024331,
"eval_overall_recall": 0.9135802469135802,
"eval_runtime": 0.2894,
"eval_samples_per_second": 587.361,
"eval_steps_per_second": 10.365,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.49956128001213074,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0796,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8932038834951457,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8932038834951457,
"eval_LOCATION_recall": 0.8932038834951457,
"eval_ORGANIZATION_f1": 0.899135446685879,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8863636363636364,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04736977815628052,
"eval_overall_accuracy": 0.9850869925434963,
"eval_overall_f1": 0.9226993865030675,
"eval_overall_precision": 0.9170731707317074,
"eval_overall_recall": 0.928395061728395,
"eval_runtime": 0.2902,
"eval_samples_per_second": 585.827,
"eval_steps_per_second": 10.338,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.6587392091751099,
"learning_rate": 4.55e-05,
"loss": 0.0721,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.9074074074074074,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8672566371681416,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.906906906906907,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.044407669454813004,
"eval_overall_accuracy": 0.9870201601767468,
"eval_overall_f1": 0.9297163995067819,
"eval_overall_precision": 0.9285714285714286,
"eval_overall_recall": 0.9308641975308642,
"eval_runtime": 0.2894,
"eval_samples_per_second": 587.507,
"eval_steps_per_second": 10.368,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.8691452145576477,
"learning_rate": 4.5e-05,
"loss": 0.0652,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.927536231884058,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9195402298850575,
"eval_ORGANIZATION_recall": 0.935672514619883,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.041865505278110504,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9437652811735942,
"eval_overall_precision": 0.9346246973365617,
"eval_overall_recall": 0.9530864197530864,
"eval_runtime": 0.2853,
"eval_samples_per_second": 595.818,
"eval_steps_per_second": 10.514,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.35112836956977844,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0626,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9116809116809117,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8888888888888888,
"eval_ORGANIZATION_recall": 0.935672514619883,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03863911330699921,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9427527405602923,
"eval_overall_precision": 0.9302884615384616,
"eval_overall_recall": 0.9555555555555556,
"eval_runtime": 0.2919,
"eval_samples_per_second": 582.328,
"eval_steps_per_second": 10.276,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.4420148730278015,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0565,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9320388349514563,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9320388349514563,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9017341040462428,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8914285714285715,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03864333778619766,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9348093480934809,
"eval_overall_precision": 0.9313725490196079,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2896,
"eval_samples_per_second": 587.075,
"eval_steps_per_second": 10.36,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.40934404730796814,
"learning_rate": 4.35e-05,
"loss": 0.0561,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9080118694362017,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03923650085926056,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9369592088998763,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2898,
"eval_samples_per_second": 586.643,
"eval_steps_per_second": 10.353,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.28298506140708923,
"learning_rate": 4.3e-05,
"loss": 0.0537,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9020771513353115,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03811865299940109,
"eval_overall_accuracy": 0.9853631593482464,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2887,
"eval_samples_per_second": 588.854,
"eval_steps_per_second": 10.392,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.3956383764743805,
"learning_rate": 4.25e-05,
"loss": 0.0522,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9514563106796117,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9514563106796117,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9043478260869565,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.896551724137931,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.033128008246421814,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9372693726937269,
"eval_overall_precision": 0.9338235294117647,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2909,
"eval_samples_per_second": 584.364,
"eval_steps_per_second": 10.312,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.7701698541641235,
"learning_rate": 4.2e-05,
"loss": 0.0466,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9226361031518625,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9044943820224719,
"eval_ORGANIZATION_recall": 0.9415204678362573,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.03562522307038307,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9424724602203182,
"eval_overall_precision": 0.9344660194174758,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2851,
"eval_samples_per_second": 596.362,
"eval_steps_per_second": 10.524,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.6282719969749451,
"learning_rate": 4.15e-05,
"loss": 0.0451,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8973607038123168,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03493789955973625,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9359605911330049,
"eval_overall_precision": 0.9336609336609336,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2881,
"eval_samples_per_second": 590.153,
"eval_steps_per_second": 10.414,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.3932057321071625,
"learning_rate": 4.1e-05,
"loss": 0.0415,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9020771513353115,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03558022901415825,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.934487021013597,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.287,
"eval_samples_per_second": 592.269,
"eval_steps_per_second": 10.452,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.568230926990509,
"learning_rate": 4.05e-05,
"loss": 0.0408,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9149560117302051,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9176470588235294,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.0325382798910141,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9421894218942188,
"eval_overall_precision": 0.9387254901960784,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2869,
"eval_samples_per_second": 592.56,
"eval_steps_per_second": 10.457,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.40318989753723145,
"learning_rate": 4e-05,
"loss": 0.0392,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03676645830273628,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9433497536945813,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2874,
"eval_samples_per_second": 591.428,
"eval_steps_per_second": 10.437,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.539707362651825,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.037,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.930232558139535,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8928571428571429,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8848484848484848,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.8538011695906432,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.046712495386600494,
"eval_overall_accuracy": 0.9850869925434963,
"eval_overall_f1": 0.9244114002478315,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9209876543209876,
"eval_runtime": 0.2867,
"eval_samples_per_second": 593.048,
"eval_steps_per_second": 10.466,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.3127209544181824,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0365,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9339622641509433,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.908256880733945,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9058823529411764,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03566086292266846,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9361179361179361,
"eval_overall_precision": 0.9315403422982885,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2911,
"eval_samples_per_second": 583.894,
"eval_steps_per_second": 10.304,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.7140548825263977,
"learning_rate": 3.85e-05,
"loss": 0.0366,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9201877934272301,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8909090909090909,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.890207715133531,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9036144578313253,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04156691953539848,
"eval_overall_accuracy": 0.9859154929577465,
"eval_overall_f1": 0.9236453201970444,
"eval_overall_precision": 0.9213759213759214,
"eval_overall_recall": 0.9259259259259259,
"eval_runtime": 0.2869,
"eval_samples_per_second": 592.586,
"eval_steps_per_second": 10.457,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 1.450055718421936,
"learning_rate": 3.8e-05,
"loss": 0.0355,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9351851851851852,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8938053097345132,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.888888888888889,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9135802469135802,
"eval_ORGANIZATION_recall": 0.8654970760233918,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.041478678584098816,
"eval_overall_accuracy": 0.9859154929577465,
"eval_overall_f1": 0.9259259259259259,
"eval_overall_precision": 0.9259259259259259,
"eval_overall_recall": 0.9259259259259259,
"eval_runtime": 0.2862,
"eval_samples_per_second": 593.984,
"eval_steps_per_second": 10.482,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.32188066840171814,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0328,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.926605504587156,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8782608695652174,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.8875379939209728,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.8538011695906432,
"eval_PERSON_f1": 0.9618320610687023,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9618320610687023,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.04481671750545502,
"eval_overall_accuracy": 0.9842584921292461,
"eval_overall_f1": 0.9221260815822003,
"eval_overall_precision": 0.9232673267326733,
"eval_overall_recall": 0.9209876543209876,
"eval_runtime": 0.2882,
"eval_samples_per_second": 589.793,
"eval_steps_per_second": 10.408,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.07386445999145508,
"learning_rate": 3.7e-05,
"loss": 0.0328,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9181286549707602,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9181286549707602,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9581749049429659,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9545454545454546,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.03761324658989906,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.288,
"eval_samples_per_second": 590.187,
"eval_steps_per_second": 10.415,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.4159574806690216,
"learning_rate": 3.65e-05,
"loss": 0.0315,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8973607038123168,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9731800766283524,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9769230769230769,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03484410420060158,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9346485819975339,
"eval_overall_precision": 0.9334975369458128,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2867,
"eval_samples_per_second": 593.008,
"eval_steps_per_second": 10.465,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.8729248046875,
"learning_rate": 3.6e-05,
"loss": 0.0292,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9565217391304348,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9519230769230769,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9101449275362319,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9022988505747126,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.03564916551113129,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.939729397293973,
"eval_overall_precision": 0.9362745098039216,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2878,
"eval_samples_per_second": 590.754,
"eval_steps_per_second": 10.425,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.5797105431556702,
"learning_rate": 3.55e-05,
"loss": 0.0281,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9769230769230769,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9844961240310077,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03710415959358215,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9408866995073891,
"eval_overall_precision": 0.9385749385749386,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2871,
"eval_samples_per_second": 592.151,
"eval_steps_per_second": 10.45,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.4047281742095947,
"learning_rate": 3.5e-05,
"loss": 0.0283,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9395348837209301,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9017857142857143,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9208211143695014,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9235294117647059,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04153118282556534,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.941320293398533,
"eval_overall_precision": 0.9322033898305084,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2842,
"eval_samples_per_second": 598.211,
"eval_steps_per_second": 10.557,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.2278306931257248,
"learning_rate": 3.45e-05,
"loss": 0.0264,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9058823529411764,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9729729729729729,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.984375,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.038342323154211044,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9359605911330049,
"eval_overall_precision": 0.9336609336609336,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2887,
"eval_samples_per_second": 588.938,
"eval_steps_per_second": 10.393,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.328101247549057,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0254,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9149560117302051,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9176470588235294,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9615384615384615,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9541984732824428,
"eval_loss": 0.04061650112271309,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9359605911330049,
"eval_overall_precision": 0.9336609336609336,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2856,
"eval_samples_per_second": 595.214,
"eval_steps_per_second": 10.504,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.40928569436073303,
"learning_rate": 3.35e-05,
"loss": 0.0269,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9573459715639812,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9351851851851852,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.03831565007567406,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9481481481481482,
"eval_overall_precision": 0.9481481481481482,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.288,
"eval_samples_per_second": 590.221,
"eval_steps_per_second": 10.416,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.16683848202228546,
"learning_rate": 3.3e-05,
"loss": 0.027,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9528301886792453,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.926605504587156,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9122807017543859,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9122807017543859,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9769230769230769,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9844961240310077,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03685828298330307,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9434889434889435,
"eval_overall_precision": 0.9388753056234719,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2876,
"eval_samples_per_second": 590.999,
"eval_steps_per_second": 10.429,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.39856961369514465,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0284,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9262536873156342,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9345238095238095,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.036390844732522964,
"eval_overall_accuracy": 0.9900579950289975,
"eval_overall_f1": 0.9446494464944649,
"eval_overall_precision": 0.9411764705882353,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.289,
"eval_samples_per_second": 588.254,
"eval_steps_per_second": 10.381,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.2952122390270233,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0214,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9483568075117371,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9181818181818182,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9294117647058824,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9349112426035503,
"eval_ORGANIZATION_recall": 0.9239766081871345,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.034952983260154724,
"eval_overall_accuracy": 0.9903341618337476,
"eval_overall_f1": 0.9508599508599508,
"eval_overall_precision": 0.9462102689486552,
"eval_overall_recall": 0.9555555555555556,
"eval_runtime": 0.2874,
"eval_samples_per_second": 591.549,
"eval_steps_per_second": 10.439,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.20993302762508392,
"learning_rate": 3.15e-05,
"loss": 0.0222,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9122807017543859,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9122807017543859,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.03949348255991936,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9371146732429099,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2839,
"eval_samples_per_second": 598.895,
"eval_steps_per_second": 10.569,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.5435236096382141,
"learning_rate": 3.1e-05,
"loss": 0.0232,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9308755760368664,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8859649122807017,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9382716049382716,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.044381432235240936,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2843,
"eval_samples_per_second": 597.937,
"eval_steps_per_second": 10.552,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.12131531536579132,
"learning_rate": 3.05e-05,
"loss": 0.0221,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9483568075117371,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9181818181818182,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9047619047619047,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04111649468541145,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9395807644882861,
"eval_overall_precision": 0.9384236453201971,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2822,
"eval_samples_per_second": 602.482,
"eval_steps_per_second": 10.632,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.28180670738220215,
"learning_rate": 3e-05,
"loss": 0.0225,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9011627906976746,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8959537572254336,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04030903801321983,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9336609336609337,
"eval_overall_precision": 0.9290953545232273,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2828,
"eval_samples_per_second": 601.094,
"eval_steps_per_second": 10.608,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.14792484045028687,
"learning_rate": 2.95e-05,
"loss": 0.0233,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03631044179201126,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9458128078817735,
"eval_overall_precision": 0.9434889434889435,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.286,
"eval_samples_per_second": 594.403,
"eval_steps_per_second": 10.489,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.08024735003709793,
"learning_rate": 2.9e-05,
"loss": 0.0226,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.039088305085897446,
"eval_overall_accuracy": 0.9900579950289975,
"eval_overall_f1": 0.9455445544554455,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2825,
"eval_samples_per_second": 601.79,
"eval_steps_per_second": 10.62,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.2308168262243271,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0213,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9080118694362017,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.040078021585941315,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9382716049382716,
"eval_overall_precision": 0.9382716049382716,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2855,
"eval_samples_per_second": 595.36,
"eval_steps_per_second": 10.506,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.3943524956703186,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0197,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9112426035502958,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.041735969483852386,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.939729397293973,
"eval_overall_precision": 0.9362745098039216,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.287,
"eval_samples_per_second": 592.296,
"eval_steps_per_second": 10.452,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.23082971572875977,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0188,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9176470588235294,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9230769230769231,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.039327267557382584,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.939729397293973,
"eval_overall_precision": 0.9362745098039216,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2872,
"eval_samples_per_second": 591.934,
"eval_steps_per_second": 10.446,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.3008003830909729,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0194,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9351851851851852,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8938053097345132,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.8961424332344213,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9096385542168675,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04397236928343773,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9300613496932515,
"eval_overall_precision": 0.9243902439024391,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2844,
"eval_samples_per_second": 597.752,
"eval_steps_per_second": 10.549,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.0939735621213913,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0185,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9117647058823529,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.040703244507312775,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2817,
"eval_samples_per_second": 603.541,
"eval_steps_per_second": 10.651,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.2692526876926422,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.018,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9345794392523364,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9009009009009009,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8988095238095237,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.046056684106588364,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9334975369458127,
"eval_overall_precision": 0.9312039312039312,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2843,
"eval_samples_per_second": 597.925,
"eval_steps_per_second": 10.552,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.049294598400592804,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0172,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.913946587537092,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04394863173365593,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9419035846724351,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2823,
"eval_samples_per_second": 602.281,
"eval_steps_per_second": 10.628,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.2389165610074997,
"learning_rate": 2.5e-05,
"loss": 0.0163,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.930232558139535,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8928571428571429,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8988095238095237,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.046086400747299194,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9312039312039312,
"eval_overall_precision": 0.9266503667481663,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2852,
"eval_samples_per_second": 596.16,
"eval_steps_per_second": 10.52,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.07716859132051468,
"learning_rate": 2.45e-05,
"loss": 0.0174,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8955223880597015,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9146341463414634,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04738534986972809,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9333333333333333,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2824,
"eval_samples_per_second": 602.026,
"eval_steps_per_second": 10.624,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.30036410689353943,
"learning_rate": 2.4e-05,
"loss": 0.0163,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9281437125748503,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.950920245398773,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04744507372379303,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.949194547707559,
"eval_overall_precision": 0.9527363184079602,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2845,
"eval_samples_per_second": 597.457,
"eval_steps_per_second": 10.543,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.5605159997940063,
"learning_rate": 2.35e-05,
"loss": 0.0169,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9107142857142856,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04924781993031502,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9358024691358025,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2836,
"eval_samples_per_second": 599.43,
"eval_steps_per_second": 10.578,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.15382979810237885,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0161,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8999999999999999,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9053254437869822,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.048174403607845306,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9359605911330049,
"eval_overall_precision": 0.9336609336609336,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2808,
"eval_samples_per_second": 605.459,
"eval_steps_per_second": 10.685,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.87953120470047,
"learning_rate": 2.25e-05,
"loss": 0.0159,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9439252336448598,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9099099099099099,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05012303590774536,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9434889434889435,
"eval_overall_precision": 0.9388753056234719,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2828,
"eval_samples_per_second": 601.164,
"eval_steps_per_second": 10.609,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.21445991098880768,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0162,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9345794392523364,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9009009009009009,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8982035928143711,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04626905918121338,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9333333333333333,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2825,
"eval_samples_per_second": 601.666,
"eval_steps_per_second": 10.618,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.2506076693534851,
"learning_rate": 2.15e-05,
"loss": 0.014,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9074626865671643,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04708336666226387,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2819,
"eval_samples_per_second": 603.096,
"eval_steps_per_second": 10.643,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.21353253722190857,
"learning_rate": 2.1e-05,
"loss": 0.0138,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9112426035502958,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.045027680695056915,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2872,
"eval_samples_per_second": 591.94,
"eval_steps_per_second": 10.446,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.12717700004577637,
"learning_rate": 2.05e-05,
"loss": 0.0128,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04736001789569855,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2854,
"eval_samples_per_second": 595.647,
"eval_steps_per_second": 10.511,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.20274725556373596,
"learning_rate": 2e-05,
"loss": 0.0152,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9080118694362017,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04336976259946823,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.284,
"eval_samples_per_second": 598.587,
"eval_steps_per_second": 10.563,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.28979969024658203,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0138,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9326923076923078,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9238095238095239,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04720545560121536,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9358024691358025,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2831,
"eval_samples_per_second": 600.495,
"eval_steps_per_second": 10.597,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.5977379083633423,
"learning_rate": 1.9e-05,
"loss": 0.0144,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04737415909767151,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9348093480934809,
"eval_overall_precision": 0.9313725490196079,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2829,
"eval_samples_per_second": 600.926,
"eval_steps_per_second": 10.605,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.7185294032096863,
"learning_rate": 1.85e-05,
"loss": 0.0125,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9528301886792453,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.926605504587156,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04819779098033905,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9434889434889435,
"eval_overall_precision": 0.9388753056234719,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2835,
"eval_samples_per_second": 599.61,
"eval_steps_per_second": 10.581,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.11835664510726929,
"learning_rate": 1.8e-05,
"loss": 0.0128,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9020771513353115,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04576900601387024,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9331683168316831,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.9308641975308642,
"eval_runtime": 0.2817,
"eval_samples_per_second": 603.382,
"eval_steps_per_second": 10.648,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.34091636538505554,
"learning_rate": 1.75e-05,
"loss": 0.0109,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05012081190943718,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9371146732429099,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2832,
"eval_samples_per_second": 600.353,
"eval_steps_per_second": 10.594,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.2389426976442337,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0138,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9144542772861357,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9226190476190477,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04875032231211662,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9408866995073891,
"eval_overall_precision": 0.9385749385749386,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2823,
"eval_samples_per_second": 602.275,
"eval_steps_per_second": 10.628,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.03752421215176582,
"learning_rate": 1.65e-05,
"loss": 0.011,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9488372093023257,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9107142857142857,
"eval_LOCATION_recall": 0.9902912621359223,
"eval_ORGANIZATION_f1": 0.9226190476190477,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04949748143553734,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.947109471094711,
"eval_overall_precision": 0.9436274509803921,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2843,
"eval_samples_per_second": 597.915,
"eval_steps_per_second": 10.551,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.27415943145751953,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0124,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9483568075117371,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9181818181818182,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9203539823008849,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9285714285714286,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05155285820364952,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9459459459459458,
"eval_overall_precision": 0.941320293398533,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2825,
"eval_samples_per_second": 601.848,
"eval_steps_per_second": 10.621,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.1705402135848999,
"learning_rate": 1.55e-05,
"loss": 0.0112,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9528301886792453,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.926605504587156,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9053254437869822,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.053939275443553925,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9408866995073891,
"eval_overall_precision": 0.9385749385749386,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2844,
"eval_samples_per_second": 597.829,
"eval_steps_per_second": 10.55,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.12086907029151917,
"learning_rate": 1.5e-05,
"loss": 0.0116,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9439252336448598,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9099099099099099,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9258160237388725,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9397590361445783,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05270753800868988,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.947109471094711,
"eval_overall_precision": 0.9436274509803921,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2883,
"eval_samples_per_second": 589.748,
"eval_steps_per_second": 10.407,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.4125543236732483,
"learning_rate": 1.45e-05,
"loss": 0.0126,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9149560117302051,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9176470588235294,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05531427264213562,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.282,
"eval_samples_per_second": 602.883,
"eval_steps_per_second": 10.639,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.015178772620856762,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0119,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055215880274772644,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9407407407407408,
"eval_overall_precision": 0.9407407407407408,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2833,
"eval_samples_per_second": 599.981,
"eval_steps_per_second": 10.588,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.3421923816204071,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0117,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9339622641509433,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.908256880733945,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9085545722713864,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05207439139485359,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9348093480934809,
"eval_overall_precision": 0.9313725490196079,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2846,
"eval_samples_per_second": 597.336,
"eval_steps_per_second": 10.541,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.014697953127324581,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0109,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9198813056379821,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9337349397590361,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.052391551434993744,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9419035846724351,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2913,
"eval_samples_per_second": 583.681,
"eval_steps_per_second": 10.3,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.8199822902679443,
"learning_rate": 1.25e-05,
"loss": 0.0119,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05018562823534012,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9433497536945813,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2857,
"eval_samples_per_second": 595.107,
"eval_steps_per_second": 10.502,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.014690599404275417,
"learning_rate": 1.2e-05,
"loss": 0.0108,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04942698031663895,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9421894218942188,
"eval_overall_precision": 0.9387254901960784,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2874,
"eval_samples_per_second": 591.578,
"eval_steps_per_second": 10.44,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.039866916835308075,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0102,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9259259259259259,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8849557522123894,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9134328358208956,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.056226395070552826,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9348093480934809,
"eval_overall_precision": 0.9313725490196079,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2845,
"eval_samples_per_second": 597.543,
"eval_steps_per_second": 10.545,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.26715323328971863,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0106,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9144542772861357,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9226190476190477,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05204785242676735,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9395807644882861,
"eval_overall_precision": 0.9384236453201971,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2894,
"eval_samples_per_second": 587.514,
"eval_steps_per_second": 10.368,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.01361830998212099,
"learning_rate": 1.05e-05,
"loss": 0.01,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9020771513353115,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05356890708208084,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.934487021013597,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2869,
"eval_samples_per_second": 592.502,
"eval_steps_per_second": 10.456,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.2177649885416031,
"learning_rate": 1e-05,
"loss": 0.0106,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9112426035502958,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05178524926304817,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9420468557336621,
"eval_overall_precision": 0.9408866995073891,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2866,
"eval_samples_per_second": 593.235,
"eval_steps_per_second": 10.469,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.2875840663909912,
"learning_rate": 9.5e-06,
"loss": 0.0109,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9176470588235294,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9230769230769231,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05085374787449837,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9433497536945813,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2852,
"eval_samples_per_second": 596.165,
"eval_steps_per_second": 10.521,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.8717382550239563,
"learning_rate": 9e-06,
"loss": 0.0107,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9203539823008849,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9285714285714286,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.053607672452926636,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9458128078817735,
"eval_overall_precision": 0.9434889434889435,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2849,
"eval_samples_per_second": 596.724,
"eval_steps_per_second": 10.53,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.22598180174827576,
"learning_rate": 8.500000000000002e-06,
"loss": 0.01,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9134328358208956,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.054290562868118286,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9419035846724351,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2865,
"eval_samples_per_second": 593.447,
"eval_steps_per_second": 10.473,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.13282036781311035,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0095,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9262536873156342,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9345238095238095,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05185828357934952,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9482758620689656,
"eval_overall_precision": 0.9459459459459459,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2836,
"eval_samples_per_second": 599.412,
"eval_steps_per_second": 10.578,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.5591405630111694,
"learning_rate": 7.5e-06,
"loss": 0.0089,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9203539823008849,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9285714285714286,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05344574898481369,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2819,
"eval_samples_per_second": 603.017,
"eval_steps_per_second": 10.641,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.05080636963248253,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0092,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9074626865671643,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.05643809959292412,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2862,
"eval_samples_per_second": 593.99,
"eval_steps_per_second": 10.482,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.04333968460559845,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.009,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05516526848077774,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9407407407407408,
"eval_overall_precision": 0.9407407407407408,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.282,
"eval_samples_per_second": 602.828,
"eval_steps_per_second": 10.638,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.10372398048639297,
"learning_rate": 6e-06,
"loss": 0.0091,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05584413930773735,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2857,
"eval_samples_per_second": 595.134,
"eval_steps_per_second": 10.502,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.8034614324569702,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0084,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.0564132034778595,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2827,
"eval_samples_per_second": 601.286,
"eval_steps_per_second": 10.611,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.12046585977077484,
"learning_rate": 5e-06,
"loss": 0.0083,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.055919669568538666,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2854,
"eval_samples_per_second": 595.724,
"eval_steps_per_second": 10.513,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.10875310003757477,
"learning_rate": 4.5e-06,
"loss": 0.0091,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9198813056379821,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9337349397590361,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.057050131261348724,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9419035846724351,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2833,
"eval_samples_per_second": 600.144,
"eval_steps_per_second": 10.591,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.225071519613266,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0091,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9258160237388725,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9397590361445783,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.054857611656188965,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9443757725587144,
"eval_overall_precision": 0.9455445544554455,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2858,
"eval_samples_per_second": 594.868,
"eval_steps_per_second": 10.498,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.06291569769382477,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0087,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055625513195991516,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2843,
"eval_samples_per_second": 598.037,
"eval_steps_per_second": 10.554,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.08525354415178299,
"learning_rate": 3e-06,
"loss": 0.01,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05541791766881943,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2838,
"eval_samples_per_second": 599.059,
"eval_steps_per_second": 10.572,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.09550740569829941,
"learning_rate": 2.5e-06,
"loss": 0.0084,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05532419681549072,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2835,
"eval_samples_per_second": 599.649,
"eval_steps_per_second": 10.582,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.06601278483867645,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0087,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9262536873156342,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9345238095238095,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05607493966817856,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9458128078817735,
"eval_overall_precision": 0.9434889434889435,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2846,
"eval_samples_per_second": 597.409,
"eval_steps_per_second": 10.543,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.27830517292022705,
"learning_rate": 1.5e-06,
"loss": 0.0085,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055903978645801544,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2846,
"eval_samples_per_second": 597.226,
"eval_steps_per_second": 10.539,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.07699746638536453,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0096,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055559732019901276,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2861,
"eval_samples_per_second": 594.286,
"eval_steps_per_second": 10.487,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.37596553564071655,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0077,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055813878774642944,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2863,
"eval_samples_per_second": 593.754,
"eval_steps_per_second": 10.478,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.10105358809232712,
"learning_rate": 0.0,
"loss": 0.0093,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9478672985781991,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9259259259259259,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.055903155356645584,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2842,
"eval_samples_per_second": 598.173,
"eval_steps_per_second": 10.556,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4325426924793372.0,
"train_loss": 0.03976734430218736,
"train_runtime": 549.4926,
"train_samples_per_second": 278.621,
"train_steps_per_second": 17.471
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4325426924793372.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}