nerui-pt-pl20-3 / trainer_state.json
apwic's picture
End of training
cf473f4 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": 1.1256990432739258,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8524,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.25146198830409355,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.2621951219512195,
"eval_ORGANIZATION_recall": 0.24157303370786518,
"eval_PERSON_f1": 0.3486842105263158,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.30113636363636365,
"eval_PERSON_recall": 0.4140625,
"eval_loss": 0.37840449810028076,
"eval_overall_accuracy": 0.8726045883940621,
"eval_overall_f1": 0.2605156037991859,
"eval_overall_precision": 0.2782608695652174,
"eval_overall_recall": 0.24489795918367346,
"eval_runtime": 0.2951,
"eval_samples_per_second": 576.008,
"eval_steps_per_second": 10.165,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.7344218492507935,
"learning_rate": 4.9e-05,
"loss": 0.3653,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.35955056179775285,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.34782608695652173,
"eval_LOCATION_recall": 0.37209302325581395,
"eval_ORGANIZATION_f1": 0.5167173252279635,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.5629139072847682,
"eval_ORGANIZATION_recall": 0.47752808988764045,
"eval_PERSON_f1": 0.621160409556314,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.5515151515151515,
"eval_PERSON_recall": 0.7109375,
"eval_loss": 0.24463514983654022,
"eval_overall_accuracy": 0.9265856950067476,
"eval_overall_f1": 0.5199999999999999,
"eval_overall_precision": 0.5098039215686274,
"eval_overall_recall": 0.5306122448979592,
"eval_runtime": 0.2962,
"eval_samples_per_second": 573.875,
"eval_steps_per_second": 10.127,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.7497644424438477,
"learning_rate": 4.85e-05,
"loss": 0.2075,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7625,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8243243243243243,
"eval_LOCATION_recall": 0.7093023255813954,
"eval_ORGANIZATION_f1": 0.7539267015706808,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7058823529411765,
"eval_ORGANIZATION_recall": 0.8089887640449438,
"eval_PERSON_f1": 0.9473684210526315,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9130434782608695,
"eval_PERSON_recall": 0.984375,
"eval_loss": 0.10795873403549194,
"eval_overall_accuracy": 0.9651821862348178,
"eval_overall_f1": 0.8193069306930691,
"eval_overall_precision": 0.7956730769230769,
"eval_overall_recall": 0.8443877551020408,
"eval_runtime": 0.2995,
"eval_samples_per_second": 567.666,
"eval_steps_per_second": 10.018,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.6917170286178589,
"learning_rate": 4.8e-05,
"loss": 0.1374,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.761904761904762,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.6990291262135923,
"eval_LOCATION_recall": 0.8372093023255814,
"eval_ORGANIZATION_f1": 0.822857142857143,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8372093023255814,
"eval_ORGANIZATION_recall": 0.8089887640449438,
"eval_PERSON_f1": 0.9729729729729729,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9618320610687023,
"eval_PERSON_recall": 0.984375,
"eval_loss": 0.08412756770849228,
"eval_overall_accuracy": 0.9735492577597841,
"eval_overall_f1": 0.8571428571428571,
"eval_overall_precision": 0.8423645320197044,
"eval_overall_recall": 0.8724489795918368,
"eval_runtime": 0.2998,
"eval_samples_per_second": 567.004,
"eval_steps_per_second": 10.006,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.5097567439079285,
"learning_rate": 4.75e-05,
"loss": 0.1114,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8571428571428571,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8426966292134831,
"eval_LOCATION_recall": 0.872093023255814,
"eval_ORGANIZATION_f1": 0.8633879781420766,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8404255319148937,
"eval_ORGANIZATION_recall": 0.8876404494382022,
"eval_PERSON_f1": 0.9729729729729729,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9618320610687023,
"eval_PERSON_recall": 0.984375,
"eval_loss": 0.0720052421092987,
"eval_overall_accuracy": 0.9781376518218623,
"eval_overall_f1": 0.8975000000000001,
"eval_overall_precision": 0.8799019607843137,
"eval_overall_recall": 0.9158163265306123,
"eval_runtime": 0.2976,
"eval_samples_per_second": 571.151,
"eval_steps_per_second": 10.079,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.5810394883155823,
"learning_rate": 4.7e-05,
"loss": 0.0921,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8491620111731845,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8172043010752689,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8739495798319328,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8715083798882681,
"eval_ORGANIZATION_recall": 0.8764044943820225,
"eval_PERSON_f1": 0.9767441860465116,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9692307692307692,
"eval_PERSON_recall": 0.984375,
"eval_loss": 0.06163949519395828,
"eval_overall_accuracy": 0.9805668016194332,
"eval_overall_f1": 0.9017632241813602,
"eval_overall_precision": 0.8905472636815921,
"eval_overall_recall": 0.9132653061224489,
"eval_runtime": 0.2985,
"eval_samples_per_second": 569.578,
"eval_steps_per_second": 10.051,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.541133463382721,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0864,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.8666666666666666,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8297872340425532,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.8943089430894309,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8638743455497382,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9689922480620154,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9615384615384616,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0567135289311409,
"eval_overall_accuracy": 0.9811066126855601,
"eval_overall_f1": 0.9120198265179678,
"eval_overall_precision": 0.8867469879518072,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.854,
"eval_steps_per_second": 10.18,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.1868620216846466,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0791,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.8967391304347827,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.868421052631579,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9609375,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9609375,
"eval_loss": 0.048262566328048706,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.916354556803995,
"eval_overall_precision": 0.8973105134474327,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.578,
"eval_steps_per_second": 10.193,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.5032618641853333,
"learning_rate": 4.55e-05,
"loss": 0.0712,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.88268156424581,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8494623655913979,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0451405793428421,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9283018867924528,
"eval_overall_precision": 0.9156327543424317,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.744,
"eval_steps_per_second": 10.16,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.7969183921813965,
"learning_rate": 4.5e-05,
"loss": 0.0653,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.8950276243093923,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8526315789473684,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9116022099447514,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8967391304347826,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04921705648303032,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9137931034482759,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.662,
"eval_steps_per_second": 10.229,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.5103535652160645,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0605,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9281767955801105,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8842105263157894,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.896358543417367,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8938547486033519,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04341064766049385,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9201995012468828,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2987,
"eval_samples_per_second": 569.117,
"eval_steps_per_second": 10.043,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.3075887858867645,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0592,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9039548022598871,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8791208791208791,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9209809264305177,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8941798941798942,
"eval_ORGANIZATION_recall": 0.949438202247191,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.037002816796302795,
"eval_overall_accuracy": 0.9875843454790824,
"eval_overall_f1": 0.9361702127659574,
"eval_overall_precision": 0.918918918918919,
"eval_overall_recall": 0.9540816326530612,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.881,
"eval_steps_per_second": 10.163,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 1.0439996719360352,
"learning_rate": 4.35e-05,
"loss": 0.0532,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9491525423728814,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9725490196078432,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9763779527559056,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04139236733317375,
"eval_overall_accuracy": 0.9878542510121457,
"eval_overall_f1": 0.9419191919191919,
"eval_overall_precision": 0.9325,
"eval_overall_recall": 0.951530612244898,
"eval_runtime": 0.2923,
"eval_samples_per_second": 581.548,
"eval_steps_per_second": 10.263,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.17437110841274261,
"learning_rate": 4.3e-05,
"loss": 0.05,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9479768786127168,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9425287356321839,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9106145251396648,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9055555555555556,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0382050946354866,
"eval_overall_accuracy": 0.9870445344129555,
"eval_overall_f1": 0.9402795425667091,
"eval_overall_precision": 0.9367088607594937,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2975,
"eval_samples_per_second": 571.373,
"eval_steps_per_second": 10.083,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.41330814361572266,
"learning_rate": 4.25e-05,
"loss": 0.0467,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9364161849710984,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9310344827586207,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9147727272727272,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9252873563218391,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9763779527559054,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9841269841269841,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.039770133793354034,
"eval_overall_accuracy": 0.9873144399460189,
"eval_overall_f1": 0.9396662387676509,
"eval_overall_precision": 0.9457364341085271,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2973,
"eval_samples_per_second": 571.776,
"eval_steps_per_second": 10.09,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.4537578225135803,
"learning_rate": 4.2e-05,
"loss": 0.0461,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.9299719887955181,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9273743016759777,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.042097028344869614,
"eval_overall_accuracy": 0.9883940620782726,
"eval_overall_f1": 0.9445843828715365,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9566326530612245,
"eval_runtime": 0.2969,
"eval_samples_per_second": 572.565,
"eval_steps_per_second": 10.104,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.2155313938856125,
"learning_rate": 4.15e-05,
"loss": 0.0407,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9310344827586208,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9204545454545454,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9388888888888889,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9285714285714286,
"eval_ORGANIZATION_recall": 0.949438202247191,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.03533349931240082,
"eval_overall_accuracy": 0.9894736842105263,
"eval_overall_f1": 0.9505703422053231,
"eval_overall_precision": 0.9445843828715366,
"eval_overall_recall": 0.9566326530612245,
"eval_runtime": 0.2963,
"eval_samples_per_second": 573.817,
"eval_steps_per_second": 10.126,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.30790233612060547,
"learning_rate": 4.1e-05,
"loss": 0.0393,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9491525423728814,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.03866806626319885,
"eval_overall_accuracy": 0.9875843454790824,
"eval_overall_f1": 0.9432534678436317,
"eval_overall_precision": 0.9326683291770573,
"eval_overall_recall": 0.9540816326530612,
"eval_runtime": 0.2951,
"eval_samples_per_second": 576.163,
"eval_steps_per_second": 10.168,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.8322476148605347,
"learning_rate": 4.05e-05,
"loss": 0.037,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9431818181818181,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9222222222222223,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9265536723163842,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9318181818181818,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04221874102950096,
"eval_overall_accuracy": 0.9881241565452091,
"eval_overall_f1": 0.9477707006369427,
"eval_overall_precision": 0.9465648854961832,
"eval_overall_recall": 0.9489795918367347,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.292,
"eval_steps_per_second": 10.17,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.3742963373661041,
"learning_rate": 4e-05,
"loss": 0.0367,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9171270718232045,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8736842105263158,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9260273972602739,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9037433155080213,
"eval_ORGANIZATION_recall": 0.949438202247191,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.051451459527015686,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9413233458177279,
"eval_overall_precision": 0.921760391198044,
"eval_overall_recall": 0.9617346938775511,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.122,
"eval_steps_per_second": 10.149,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.7486676573753357,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0333,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9239130434782609,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8673469387755102,
"eval_LOCATION_recall": 0.9883720930232558,
"eval_ORGANIZATION_f1": 0.9213483146067416,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9213483146067416,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.03921040520071983,
"eval_overall_accuracy": 0.9875843454790824,
"eval_overall_f1": 0.9408805031446542,
"eval_overall_precision": 0.9280397022332506,
"eval_overall_recall": 0.9540816326530612,
"eval_runtime": 0.2967,
"eval_samples_per_second": 573.01,
"eval_steps_per_second": 10.112,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.8446559906005859,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0336,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9273743016759777,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8924731182795699,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9269662921348315,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9269662921348315,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.043164316564798355,
"eval_overall_accuracy": 0.9870445344129555,
"eval_overall_f1": 0.9443037974683544,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.951530612244898,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.551,
"eval_steps_per_second": 10.192,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.4441474378108978,
"learning_rate": 3.85e-05,
"loss": 0.0308,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9204545454545455,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9173789173789175,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.930635838150289,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04836750030517578,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.937420178799489,
"eval_overall_precision": 0.9386189258312021,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2998,
"eval_samples_per_second": 567.012,
"eval_steps_per_second": 10.006,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.18791325390338898,
"learning_rate": 3.8e-05,
"loss": 0.0327,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9273743016759777,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8924731182795699,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04768701270222664,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9390862944162437,
"eval_overall_precision": 0.9343434343434344,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2986,
"eval_samples_per_second": 569.332,
"eval_steps_per_second": 10.047,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.3290807008743286,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0319,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9204545454545455,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9261363636363636,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9367816091954023,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05026085302233696,
"eval_overall_accuracy": 0.9867746288798921,
"eval_overall_f1": 0.9413265306122449,
"eval_overall_precision": 0.9413265306122449,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2946,
"eval_samples_per_second": 577.098,
"eval_steps_per_second": 10.184,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.09288707375526428,
"learning_rate": 3.7e-05,
"loss": 0.0285,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9378531073446328,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9120879120879121,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.048738643527030945,
"eval_overall_accuracy": 0.9865047233468286,
"eval_overall_f1": 0.9441624365482234,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9489795918367347,
"eval_runtime": 0.2964,
"eval_samples_per_second": 573.603,
"eval_steps_per_second": 10.122,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.4679638743400574,
"learning_rate": 3.65e-05,
"loss": 0.0268,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9378531073446328,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.9120879120879121,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9243697478991597,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9217877094972067,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04797738045454025,
"eval_overall_accuracy": 0.9867746288798921,
"eval_overall_f1": 0.9443037974683544,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.951530612244898,
"eval_runtime": 0.2967,
"eval_samples_per_second": 573.02,
"eval_steps_per_second": 10.112,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.36331695318222046,
"learning_rate": 3.6e-05,
"loss": 0.0288,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9142857142857143,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.898876404494382,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9222222222222223,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9120879120879121,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04569070786237717,
"eval_overall_accuracy": 0.9865047233468286,
"eval_overall_f1": 0.9380530973451328,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2975,
"eval_samples_per_second": 571.411,
"eval_steps_per_second": 10.084,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.7216880917549133,
"learning_rate": 3.55e-05,
"loss": 0.0227,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9243697478991597,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9217877094972067,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05735792964696884,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.935687263556116,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2922,
"eval_samples_per_second": 581.708,
"eval_steps_per_second": 10.265,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.28201109170913696,
"learning_rate": 3.5e-05,
"loss": 0.0263,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9273743016759777,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8924731182795699,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9054441260744985,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9239766081871345,
"eval_ORGANIZATION_recall": 0.8876404494382022,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06267464905977249,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9324840764331209,
"eval_overall_precision": 0.9312977099236641,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2925,
"eval_samples_per_second": 581.098,
"eval_steps_per_second": 10.255,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.7475817203521729,
"learning_rate": 3.45e-05,
"loss": 0.0258,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9120879120879122,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8645833333333334,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.905982905982906,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9190751445086706,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.049155112355947495,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9302915082382762,
"eval_overall_precision": 0.924433249370277,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2939,
"eval_samples_per_second": 578.477,
"eval_steps_per_second": 10.208,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.10591016709804535,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0245,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9101123595505618,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8804347826086957,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9008498583569405,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9085714285714286,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04812262952327728,
"eval_overall_accuracy": 0.9859649122807017,
"eval_overall_f1": 0.9275730622617534,
"eval_overall_precision": 0.9240506329113924,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.725,
"eval_steps_per_second": 10.195,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.3404691219329834,
"learning_rate": 3.35e-05,
"loss": 0.0236,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.04825847968459129,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9392405063291138,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2961,
"eval_samples_per_second": 574.178,
"eval_steps_per_second": 10.133,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.271597295999527,
"learning_rate": 3.3e-05,
"loss": 0.0209,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.9096045197740114,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9147727272727273,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.054563164710998535,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.9331651954602775,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2931,
"eval_samples_per_second": 580.007,
"eval_steps_per_second": 10.235,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.6089611649513245,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0211,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9213483146067417,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8913043478260869,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9106145251396648,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9055555555555556,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.054925356060266495,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9331651954602775,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2922,
"eval_samples_per_second": 581.884,
"eval_steps_per_second": 10.269,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.6711059212684631,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0228,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9032258064516129,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.84,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.8914285714285715,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9069767441860465,
"eval_ORGANIZATION_recall": 0.8764044943820225,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.054428864270448685,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.9217171717171717,
"eval_overall_precision": 0.9125,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.438,
"eval_steps_per_second": 10.225,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.7363920211791992,
"learning_rate": 3.15e-05,
"loss": 0.0191,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9028571428571427,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8876404494382022,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9187675070028011,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9162011173184358,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.057144783437252045,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.934010152284264,
"eval_overall_precision": 0.9292929292929293,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.22,
"eval_steps_per_second": 10.169,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.6516408920288086,
"learning_rate": 3.1e-05,
"loss": 0.0208,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.8997134670487107,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9181286549707602,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06715705990791321,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9273885350318473,
"eval_overall_precision": 0.926208651399491,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2979,
"eval_samples_per_second": 570.692,
"eval_steps_per_second": 10.071,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.33553728461265564,
"learning_rate": 3.05e-05,
"loss": 0.0189,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9090909090909092,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9019607843137254,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8994413407821229,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.058930374681949615,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9277566539923955,
"eval_overall_precision": 0.9219143576826196,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2946,
"eval_samples_per_second": 577.021,
"eval_steps_per_second": 10.183,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.3787616491317749,
"learning_rate": 3e-05,
"loss": 0.019,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9142857142857143,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.898876404494382,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9050279329608939,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05266658589243889,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.929113924050633,
"eval_overall_precision": 0.9221105527638191,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.609,
"eval_steps_per_second": 10.175,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.022859979420900345,
"learning_rate": 2.95e-05,
"loss": 0.0187,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9080459770114941,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8977272727272727,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.895774647887324,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8983050847457628,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.051135558634996414,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9248407643312102,
"eval_overall_precision": 0.9236641221374046,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.818,
"eval_steps_per_second": 10.197,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.24190235137939453,
"learning_rate": 2.9e-05,
"loss": 0.0175,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9142857142857143,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.898876404494382,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9187675070028011,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9162011173184358,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.056694477796554565,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.9365482233502538,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.836,
"eval_steps_per_second": 10.197,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.11353705823421478,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0186,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9152542372881357,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8901098901098901,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9204545454545454,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9310344827586207,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.056940700858831406,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.937579617834395,
"eval_overall_precision": 0.9363867684478372,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2976,
"eval_samples_per_second": 571.15,
"eval_steps_per_second": 10.079,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.06498357653617859,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0166,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9130434782608695,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9767441860465116,
"eval_ORGANIZATION_f1": 0.9230769230769231,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9364161849710982,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06959273666143417,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9380530973451328,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2959,
"eval_samples_per_second": 574.608,
"eval_steps_per_second": 10.14,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.6757193803787231,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.018,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9152542372881357,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8901098901098901,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9142857142857143,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9302325581395349,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.056078676134347916,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.9348659003831418,
"eval_overall_precision": 0.9360613810741688,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.298,
"eval_samples_per_second": 570.468,
"eval_steps_per_second": 10.067,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.4513480067253113,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0159,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.8972972972972972,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8383838383838383,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9002849002849002,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9132947976878613,
"eval_ORGANIZATION_recall": 0.8876404494382022,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07361128181219101,
"eval_overall_accuracy": 0.9824561403508771,
"eval_overall_f1": 0.9242424242424242,
"eval_overall_precision": 0.915,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2967,
"eval_samples_per_second": 572.926,
"eval_steps_per_second": 10.11,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.16621187329292297,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0158,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9070422535211267,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9096045197740112,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05834043025970459,
"eval_overall_accuracy": 0.9835357624831309,
"eval_overall_f1": 0.9279393173198484,
"eval_overall_precision": 0.9197994987468672,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.169,
"eval_steps_per_second": 10.185,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.07447110116481781,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0141,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9152542372881356,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9204545454545454,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05934324860572815,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.929113924050633,
"eval_overall_precision": 0.9221105527638191,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2944,
"eval_samples_per_second": 577.405,
"eval_steps_per_second": 10.189,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.10729774087667465,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0151,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9090909090909092,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05733995884656906,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9365482233502538,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2936,
"eval_samples_per_second": 579.053,
"eval_steps_per_second": 10.219,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.06825707107782364,
"learning_rate": 2.5e-05,
"loss": 0.0149,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9101123595505618,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8804347826086957,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9375000000000001,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9482758620689655,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0580214262008667,
"eval_overall_accuracy": 0.9870445344129555,
"eval_overall_f1": 0.9440203562340966,
"eval_overall_precision": 0.9416243654822335,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.591,
"eval_steps_per_second": 10.193,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.1235552653670311,
"learning_rate": 2.45e-05,
"loss": 0.0135,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9352112676056338,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9378531073446328,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0561089925467968,
"eval_overall_accuracy": 0.9870445344129555,
"eval_overall_f1": 0.9390862944162437,
"eval_overall_precision": 0.9343434343434344,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.466,
"eval_steps_per_second": 10.226,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.16985885798931122,
"learning_rate": 2.4e-05,
"loss": 0.0142,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.902506963788301,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8950276243093923,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06791975349187851,
"eval_overall_accuracy": 0.9835357624831309,
"eval_overall_f1": 0.9232704402515723,
"eval_overall_precision": 0.9106699751861043,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.696,
"eval_steps_per_second": 10.23,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.18622367084026337,
"learning_rate": 2.35e-05,
"loss": 0.0135,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9039548022598871,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8791208791208791,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9411764705882353,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9385474860335196,
"eval_ORGANIZATION_recall": 0.9438202247191011,
"eval_PERSON_f1": 0.9803921568627452,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.984251968503937,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.05969115346670151,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9455006337135614,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.951530612244898,
"eval_runtime": 0.2951,
"eval_samples_per_second": 576.102,
"eval_steps_per_second": 10.167,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.3247317969799042,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0138,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.8813559322033897,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.9192200557103065,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9116022099447514,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06083739176392555,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9292929292929293,
"eval_overall_precision": 0.92,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2986,
"eval_samples_per_second": 569.415,
"eval_steps_per_second": 10.048,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.4509217441082001,
"learning_rate": 2.25e-05,
"loss": 0.013,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.892128279883382,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.8595505617977528,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06479934602975845,
"eval_overall_accuracy": 0.982995951417004,
"eval_overall_f1": 0.9214929214929215,
"eval_overall_precision": 0.9298701298701298,
"eval_overall_recall": 0.9132653061224489,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.708,
"eval_steps_per_second": 10.195,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.4112468957901001,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0126,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9195402298850575,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06431104987859726,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9273885350318473,
"eval_overall_precision": 0.926208651399491,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.732,
"eval_steps_per_second": 10.16,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.26832810044288635,
"learning_rate": 2.15e-05,
"loss": 0.012,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9039548022598871,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8791208791208791,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9243697478991597,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9217877094972067,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06893935799598694,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9355246523388117,
"eval_overall_precision": 0.9273182957393483,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.888,
"eval_steps_per_second": 10.163,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.038234058767557144,
"learning_rate": 2.1e-05,
"loss": 0.0115,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9048991354466859,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07218018174171448,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9273885350318473,
"eval_overall_precision": 0.926208651399491,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.075,
"eval_steps_per_second": 10.201,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.761320948600769,
"learning_rate": 2.05e-05,
"loss": 0.0126,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.88268156424581,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8494623655913979,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9164265129682998,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9408284023668639,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06757570803165436,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.928388746803069,
"eval_overall_precision": 0.9307692307692308,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.2936,
"eval_samples_per_second": 578.924,
"eval_steps_per_second": 10.216,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.2740951180458069,
"learning_rate": 2e-05,
"loss": 0.0128,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.888888888888889,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.851063829787234,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9096045197740114,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9147727272727273,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06269567459821701,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.9265822784810125,
"eval_overall_precision": 0.9195979899497487,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2936,
"eval_samples_per_second": 579.111,
"eval_steps_per_second": 10.22,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.05976470932364464,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0122,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9039548022598871,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8791208791208791,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0623447522521019,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9365482233502538,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2987,
"eval_samples_per_second": 569.077,
"eval_steps_per_second": 10.043,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.43376868963241577,
"learning_rate": 1.9e-05,
"loss": 0.0118,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9126760563380282,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9152542372881356,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06252029538154602,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9279393173198484,
"eval_overall_precision": 0.9197994987468672,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2977,
"eval_samples_per_second": 571.054,
"eval_steps_per_second": 10.077,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.14774742722511292,
"learning_rate": 1.85e-05,
"loss": 0.0092,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.8977272727272728,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8777777777777778,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9299719887955181,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9273743016759777,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0660567358136177,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9367088607594937,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2969,
"eval_samples_per_second": 572.526,
"eval_steps_per_second": 10.103,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.06450632959604263,
"learning_rate": 1.8e-05,
"loss": 0.0091,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.8876404494382023,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8586956521739131,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9152542372881356,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9204545454545454,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0651075467467308,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9289340101522842,
"eval_overall_precision": 0.9242424242424242,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2936,
"eval_samples_per_second": 578.934,
"eval_steps_per_second": 10.216,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.0688806101679802,
"learning_rate": 1.75e-05,
"loss": 0.0107,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9325842696629213,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9325842696629213,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06350100040435791,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9367088607594937,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.02,
"eval_steps_per_second": 10.2,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.4749813973903656,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.009,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06621392071247101,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9329962073324906,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.294,
"eval_samples_per_second": 578.251,
"eval_steps_per_second": 10.204,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.011679776012897491,
"learning_rate": 1.65e-05,
"loss": 0.0109,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.8839779005524862,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8421052631578947,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.905982905982906,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9190751445086706,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07114541530609131,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.9226869455006337,
"eval_overall_precision": 0.9168765743073047,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2995,
"eval_samples_per_second": 567.619,
"eval_steps_per_second": 10.017,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.4476849436759949,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0093,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9261363636363636,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9367816091954023,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06695590168237686,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9338422391857506,
"eval_overall_precision": 0.9314720812182741,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2972,
"eval_samples_per_second": 572.001,
"eval_steps_per_second": 10.094,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.23546628654003143,
"learning_rate": 1.55e-05,
"loss": 0.0104,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9126760563380282,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9152542372881356,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0661647766828537,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.929113924050633,
"eval_overall_precision": 0.9221105527638191,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2985,
"eval_samples_per_second": 569.474,
"eval_steps_per_second": 10.05,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.5799188017845154,
"learning_rate": 1.5e-05,
"loss": 0.0098,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9121813031161473,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.92,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06885422766208649,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9314720812182741,
"eval_overall_precision": 0.9267676767676768,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2932,
"eval_samples_per_second": 579.851,
"eval_steps_per_second": 10.233,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.37226343154907227,
"learning_rate": 1.45e-05,
"loss": 0.0086,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9329608938547486,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9277777777777778,
"eval_ORGANIZATION_recall": 0.9382022471910112,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06553326547145844,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9368686868686869,
"eval_overall_precision": 0.9275,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.3009,
"eval_samples_per_second": 564.996,
"eval_steps_per_second": 9.971,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.037795793265104294,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0101,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.8926553672316384,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8681318681318682,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.8933717579250721,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.8707865168539326,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0688675120472908,
"eval_overall_accuracy": 0.9827260458839406,
"eval_overall_f1": 0.9193341869398208,
"eval_overall_precision": 0.922879177377892,
"eval_overall_recall": 0.9158163265306123,
"eval_runtime": 0.2966,
"eval_samples_per_second": 573.248,
"eval_steps_per_second": 10.116,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.47558140754699707,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.011,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.8876404494382023,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8586956521739131,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9121813031161473,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.92,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06321831792593002,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9263959390862943,
"eval_overall_precision": 0.9217171717171717,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.603,
"eval_steps_per_second": 10.228,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.0527472198009491,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0089,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.905982905982906,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9190751445086706,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07013431936502457,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9275730622617534,
"eval_overall_precision": 0.9240506329113924,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.786,
"eval_steps_per_second": 10.179,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.45165157318115234,
"learning_rate": 1.25e-05,
"loss": 0.0084,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.888888888888889,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.851063829787234,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9204545454545454,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9310344827586207,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0707746222615242,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9302915082382762,
"eval_overall_precision": 0.924433249370277,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2936,
"eval_samples_per_second": 578.979,
"eval_steps_per_second": 10.217,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.1744987964630127,
"learning_rate": 1.2e-05,
"loss": 0.0092,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.8876404494382023,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8586956521739131,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9265536723163842,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9318181818181818,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06451594084501266,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.251,
"eval_steps_per_second": 10.169,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.017964554950594902,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0079,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9287749287749287,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9421965317919075,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06840353459119797,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.937579617834395,
"eval_overall_precision": 0.9363867684478372,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.633,
"eval_steps_per_second": 10.194,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.2629311978816986,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0085,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9265536723163842,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9318181818181818,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06581328809261322,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.935361216730038,
"eval_overall_precision": 0.929471032745592,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2929,
"eval_samples_per_second": 580.5,
"eval_steps_per_second": 10.244,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.07186750322580338,
"learning_rate": 1.05e-05,
"loss": 0.0083,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9265536723163842,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9318181818181818,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9765625,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9765625,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06744226813316345,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.935361216730038,
"eval_overall_precision": 0.929471032745592,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.3003,
"eval_samples_per_second": 566.104,
"eval_steps_per_second": 9.99,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.10484962165355682,
"learning_rate": 1e-05,
"loss": 0.0079,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9183098591549295,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9209039548022598,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07347893714904785,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9316455696202531,
"eval_overall_precision": 0.9246231155778895,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2932,
"eval_samples_per_second": 579.823,
"eval_steps_per_second": 10.232,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.17218157649040222,
"learning_rate": 9.5e-06,
"loss": 0.0077,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9295774647887324,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9322033898305084,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06925556808710098,
"eval_overall_accuracy": 0.9859649122807017,
"eval_overall_f1": 0.9367088607594937,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2951,
"eval_samples_per_second": 576.152,
"eval_steps_per_second": 10.167,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.28462645411491394,
"learning_rate": 9e-06,
"loss": 0.009,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9265536723163842,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9318181818181818,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0702722892165184,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.935361216730038,
"eval_overall_precision": 0.929471032745592,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.747,
"eval_steps_per_second": 10.196,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.6892483830451965,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0093,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.8977272727272728,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8777777777777778,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9096045197740114,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9147727272727273,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.06590474396944046,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9275730622617534,
"eval_overall_precision": 0.9240506329113924,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.251,
"eval_steps_per_second": 10.169,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.10835030674934387,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0069,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0693618580698967,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9314720812182741,
"eval_overall_precision": 0.9267676767676768,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2946,
"eval_samples_per_second": 577.007,
"eval_steps_per_second": 10.182,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.5486595034599304,
"learning_rate": 7.5e-06,
"loss": 0.0082,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9183098591549295,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9209039548022598,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0692315325140953,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9316455696202531,
"eval_overall_precision": 0.9246231155778895,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2929,
"eval_samples_per_second": 580.413,
"eval_steps_per_second": 10.243,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.36396417021751404,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0074,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9235127478753541,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9314285714285714,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07096973806619644,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2957,
"eval_samples_per_second": 574.936,
"eval_steps_per_second": 10.146,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.16265970468521118,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0075,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9039548022598871,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8791208791208791,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9291784702549575,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9371428571428572,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07266160100698471,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.9377382465057178,
"eval_overall_precision": 0.9341772151898734,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2963,
"eval_samples_per_second": 573.825,
"eval_steps_per_second": 10.126,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.2787863612174988,
"learning_rate": 6e-06,
"loss": 0.0072,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.92090395480226,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9261363636363636,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07234236598014832,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9316455696202531,
"eval_overall_precision": 0.9246231155778895,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.613,
"eval_steps_per_second": 10.158,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.11660141497850418,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0059,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.893854748603352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8602150537634409,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.92090395480226,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9261363636363636,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0735221803188324,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9316455696202531,
"eval_overall_precision": 0.9246231155778895,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.839,
"eval_steps_per_second": 10.197,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.07081963866949081,
"learning_rate": 5e-06,
"loss": 0.007,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9090909090909092,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9239436619718311,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9265536723163842,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07254685461521149,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.9365482233502538,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2941,
"eval_samples_per_second": 577.962,
"eval_steps_per_second": 10.199,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.02052818238735199,
"learning_rate": 4.5e-06,
"loss": 0.0074,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9318181818181818,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9425287356321839,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07222301512956619,
"eval_overall_accuracy": 0.9862348178137652,
"eval_overall_f1": 0.9390862944162437,
"eval_overall_precision": 0.9343434343434344,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.543,
"eval_steps_per_second": 10.227,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.04826980456709862,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0073,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.8999999999999999,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8617021276595744,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9121813031161473,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.92,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07453794032335281,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.929113924050633,
"eval_overall_precision": 0.9221105527638191,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.088,
"eval_steps_per_second": 10.149,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.2347097545862198,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0071,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.8999999999999999,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8617021276595744,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9121813031161473,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.92,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07519923150539398,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.929113924050633,
"eval_overall_precision": 0.9221105527638191,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2935,
"eval_samples_per_second": 579.3,
"eval_steps_per_second": 10.223,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.5050498247146606,
"learning_rate": 3e-06,
"loss": 0.0076,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.0738091990351677,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2957,
"eval_samples_per_second": 574.969,
"eval_steps_per_second": 10.147,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.38728073239326477,
"learning_rate": 2.5e-06,
"loss": 0.0072,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07277553528547287,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.9,
"eval_steps_per_second": 10.163,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.02341538295149803,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0072,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07322042435407639,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2979,
"eval_samples_per_second": 570.639,
"eval_steps_per_second": 10.07,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.013558967970311642,
"learning_rate": 1.5e-06,
"loss": 0.0072,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07443853467702866,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2936,
"eval_samples_per_second": 578.932,
"eval_steps_per_second": 10.216,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.017207574099302292,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0079,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07405915856361389,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2935,
"eval_samples_per_second": 579.287,
"eval_steps_per_second": 10.223,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.05300958827137947,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0059,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9050279329608939,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8709677419354839,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9178470254957507,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9257142857142857,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07383523136377335,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9328263624841572,
"eval_overall_precision": 0.9269521410579346,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.608,
"eval_steps_per_second": 10.175,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.013699240051209927,
"learning_rate": 0.0,
"loss": 0.0068,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.898876404494382,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8695652173913043,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9152542372881356,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9204545454545454,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9727626459143969,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9689922480620154,
"eval_PERSON_recall": 0.9765625,
"eval_loss": 0.07373205572366714,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9302915082382762,
"eval_overall_precision": 0.924433249370277,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.294,
"eval_samples_per_second": 578.322,
"eval_steps_per_second": 10.206,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4315798421360676.0,
"train_loss": 0.03683100602279107,
"train_runtime": 560.5784,
"train_samples_per_second": 273.111,
"train_steps_per_second": 17.125
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4315798421360676.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}