nerui-seq_bn-rf64-3 / trainer_state.json
apwic's picture
End of training
c8d7a8c 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": 1.313410997390747,
"learning_rate": 4.9500000000000004e-05,
"loss": 1.062,
"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": 0.0,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.0,
"eval_ORGANIZATION_recall": 0.0,
"eval_PERSON_f1": 0.0,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.0,
"eval_PERSON_recall": 0.0,
"eval_loss": 0.6283418536186218,
"eval_overall_accuracy": 0.8434547908232118,
"eval_overall_f1": 0.0,
"eval_overall_precision": 0.0,
"eval_overall_recall": 0.0,
"eval_runtime": 0.2523,
"eval_samples_per_second": 673.91,
"eval_steps_per_second": 11.893,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.9707840085029602,
"learning_rate": 4.9e-05,
"loss": 0.5934,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.08823529411764706,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.34615384615384615,
"eval_ORGANIZATION_recall": 0.05056179775280899,
"eval_PERSON_f1": 0.1111111111111111,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.2647058823529412,
"eval_PERSON_recall": 0.0703125,
"eval_loss": 0.4368453919887543,
"eval_overall_accuracy": 0.8507422402159244,
"eval_overall_f1": 0.07947019867549669,
"eval_overall_precision": 0.29508196721311475,
"eval_overall_recall": 0.04591836734693878,
"eval_runtime": 0.2404,
"eval_samples_per_second": 707.076,
"eval_steps_per_second": 12.478,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.9792824387550354,
"learning_rate": 4.85e-05,
"loss": 0.4331,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.29310344827586204,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.5666666666666667,
"eval_LOCATION_recall": 0.19767441860465115,
"eval_ORGANIZATION_f1": 0.3954802259887006,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.3977272727272727,
"eval_ORGANIZATION_recall": 0.39325842696629215,
"eval_PERSON_f1": 0.40764331210191085,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.34408602150537637,
"eval_PERSON_recall": 0.5,
"eval_loss": 0.32036030292510986,
"eval_overall_accuracy": 0.8955465587044534,
"eval_overall_f1": 0.3852040816326531,
"eval_overall_precision": 0.3852040816326531,
"eval_overall_recall": 0.3852040816326531,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.933,
"eval_steps_per_second": 12.387,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.7342562675476074,
"learning_rate": 4.8e-05,
"loss": 0.3496,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.44594594594594594,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.532258064516129,
"eval_LOCATION_recall": 0.38372093023255816,
"eval_ORGANIZATION_f1": 0.4936386768447837,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.4511627906976744,
"eval_ORGANIZATION_recall": 0.5449438202247191,
"eval_PERSON_f1": 0.49848024316109424,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.4079601990049751,
"eval_PERSON_recall": 0.640625,
"eval_loss": 0.27694153785705566,
"eval_overall_accuracy": 0.9192982456140351,
"eval_overall_f1": 0.4873563218390805,
"eval_overall_precision": 0.4435146443514644,
"eval_overall_recall": 0.5408163265306123,
"eval_runtime": 0.2484,
"eval_samples_per_second": 684.301,
"eval_steps_per_second": 12.076,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.7535701990127563,
"learning_rate": 4.75e-05,
"loss": 0.303,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.4864864864864865,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.5806451612903226,
"eval_LOCATION_recall": 0.4186046511627907,
"eval_ORGANIZATION_f1": 0.565947242206235,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.49372384937238495,
"eval_ORGANIZATION_recall": 0.6629213483146067,
"eval_PERSON_f1": 0.5833333333333334,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.4945652173913043,
"eval_PERSON_recall": 0.7109375,
"eval_loss": 0.24268952012062073,
"eval_overall_accuracy": 0.9314439946018893,
"eval_overall_f1": 0.5587229190421893,
"eval_overall_precision": 0.5051546391752577,
"eval_overall_recall": 0.625,
"eval_runtime": 0.2471,
"eval_samples_per_second": 688.042,
"eval_steps_per_second": 12.142,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 1.0798269510269165,
"learning_rate": 4.7e-05,
"loss": 0.2698,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.608695652173913,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.6533333333333333,
"eval_LOCATION_recall": 0.5697674418604651,
"eval_ORGANIZATION_f1": 0.631578947368421,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.5701357466063348,
"eval_ORGANIZATION_recall": 0.7078651685393258,
"eval_PERSON_f1": 0.6959459459459459,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.6130952380952381,
"eval_PERSON_recall": 0.8046875,
"eval_loss": 0.20958775281906128,
"eval_overall_accuracy": 0.9438596491228071,
"eval_overall_f1": 0.6495327102803738,
"eval_overall_precision": 0.5991379310344828,
"eval_overall_recall": 0.7091836734693877,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.57,
"eval_steps_per_second": 12.098,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 1.4098148345947266,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.2305,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.6428571428571429,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.6585365853658537,
"eval_LOCATION_recall": 0.627906976744186,
"eval_ORGANIZATION_f1": 0.6952141057934508,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.6301369863013698,
"eval_ORGANIZATION_recall": 0.7752808988764045,
"eval_PERSON_f1": 0.8071428571428572,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.743421052631579,
"eval_PERSON_recall": 0.8828125,
"eval_loss": 0.17846328020095825,
"eval_overall_accuracy": 0.9557354925775978,
"eval_overall_f1": 0.7218934911242604,
"eval_overall_precision": 0.673289183222958,
"eval_overall_recall": 0.7780612244897959,
"eval_runtime": 0.2475,
"eval_samples_per_second": 686.75,
"eval_steps_per_second": 12.119,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.4911014139652252,
"learning_rate": 4.600000000000001e-05,
"loss": 0.1941,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.7573964497041421,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7710843373493976,
"eval_LOCATION_recall": 0.7441860465116279,
"eval_ORGANIZATION_f1": 0.7540983606557377,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7340425531914894,
"eval_ORGANIZATION_recall": 0.7752808988764045,
"eval_PERSON_f1": 0.8550185873605947,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.8156028368794326,
"eval_PERSON_recall": 0.8984375,
"eval_loss": 0.14757227897644043,
"eval_overall_accuracy": 0.9641025641025641,
"eval_overall_f1": 0.7885572139303483,
"eval_overall_precision": 0.7694174757281553,
"eval_overall_recall": 0.8086734693877551,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.395,
"eval_steps_per_second": 12.148,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.7438257932662964,
"learning_rate": 4.55e-05,
"loss": 0.1651,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.7932960893854749,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7634408602150538,
"eval_LOCATION_recall": 0.8255813953488372,
"eval_ORGANIZATION_f1": 0.7872340425531915,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7474747474747475,
"eval_ORGANIZATION_recall": 0.8314606741573034,
"eval_PERSON_f1": 0.8773234200743494,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.8368794326241135,
"eval_PERSON_recall": 0.921875,
"eval_loss": 0.12540873885154724,
"eval_overall_accuracy": 0.9665317139001349,
"eval_overall_f1": 0.8179611650485438,
"eval_overall_precision": 0.7800925925925926,
"eval_overall_recall": 0.8596938775510204,
"eval_runtime": 0.2478,
"eval_samples_per_second": 686.14,
"eval_steps_per_second": 12.108,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.9349628686904907,
"learning_rate": 4.5e-05,
"loss": 0.1432,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.7845303867403315,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7473684210526316,
"eval_LOCATION_recall": 0.8255813953488372,
"eval_ORGANIZATION_f1": 0.8000000000000002,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7708333333333334,
"eval_ORGANIZATION_recall": 0.8314606741573034,
"eval_PERSON_f1": 0.9166666666666666,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.8897058823529411,
"eval_PERSON_recall": 0.9453125,
"eval_loss": 0.11015301942825317,
"eval_overall_accuracy": 0.9689608636977058,
"eval_overall_f1": 0.8343558282208589,
"eval_overall_precision": 0.8037825059101655,
"eval_overall_recall": 0.8673469387755102,
"eval_runtime": 0.2484,
"eval_samples_per_second": 684.352,
"eval_steps_per_second": 12.077,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.901933491230011,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.1296,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.7783783783783784,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7272727272727273,
"eval_LOCATION_recall": 0.8372093023255814,
"eval_ORGANIZATION_f1": 0.7914438502673796,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7551020408163265,
"eval_ORGANIZATION_recall": 0.8314606741573034,
"eval_PERSON_f1": 0.9393939393939394,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9117647058823529,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.10100546479225159,
"eval_overall_accuracy": 0.970310391363023,
"eval_overall_f1": 0.8359659781287971,
"eval_overall_precision": 0.7981438515081206,
"eval_overall_recall": 0.8775510204081632,
"eval_runtime": 0.2479,
"eval_samples_per_second": 685.623,
"eval_steps_per_second": 12.099,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 1.210007905960083,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.1207,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.7978142076502732,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7525773195876289,
"eval_LOCATION_recall": 0.8488372093023255,
"eval_ORGANIZATION_f1": 0.8235294117647058,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7857142857142857,
"eval_ORGANIZATION_recall": 0.8651685393258427,
"eval_PERSON_f1": 0.9288389513108614,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.8920863309352518,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.09453409910202026,
"eval_overall_accuracy": 0.9713900134952766,
"eval_overall_f1": 0.8519417475728155,
"eval_overall_precision": 0.8125,
"eval_overall_recall": 0.8954081632653061,
"eval_runtime": 0.2471,
"eval_samples_per_second": 687.844,
"eval_steps_per_second": 12.138,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 1.1103246212005615,
"learning_rate": 4.35e-05,
"loss": 0.11,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.7955801104972375,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7578947368421053,
"eval_LOCATION_recall": 0.8372093023255814,
"eval_ORGANIZATION_f1": 0.8337874659400545,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8095238095238095,
"eval_ORGANIZATION_recall": 0.8595505617977528,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.08594363927841187,
"eval_overall_accuracy": 0.9751686909581646,
"eval_overall_f1": 0.8670807453416148,
"eval_overall_precision": 0.8450363196125908,
"eval_overall_recall": 0.8903061224489796,
"eval_runtime": 0.2479,
"eval_samples_per_second": 685.644,
"eval_steps_per_second": 12.1,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.7462493777275085,
"learning_rate": 4.3e-05,
"loss": 0.1041,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.7845303867403315,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7473684210526316,
"eval_LOCATION_recall": 0.8255813953488372,
"eval_ORGANIZATION_f1": 0.8088642659279779,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.7978142076502732,
"eval_ORGANIZATION_recall": 0.8202247191011236,
"eval_PERSON_f1": 0.950191570881226,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9323308270676691,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.08413072675466537,
"eval_overall_accuracy": 0.9730094466936572,
"eval_overall_f1": 0.8493150684931507,
"eval_overall_precision": 0.829683698296837,
"eval_overall_recall": 0.8698979591836735,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.479,
"eval_steps_per_second": 12.379,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.9650947451591492,
"learning_rate": 4.25e-05,
"loss": 0.1023,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.8089887640449438,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.782608695652174,
"eval_LOCATION_recall": 0.8372093023255814,
"eval_ORGANIZATION_f1": 0.8594594594594595,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.828125,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9612403100775193,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9538461538461539,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.07779460400342941,
"eval_overall_accuracy": 0.9765182186234818,
"eval_overall_f1": 0.880893300248139,
"eval_overall_precision": 0.857487922705314,
"eval_overall_recall": 0.9056122448979592,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.818,
"eval_steps_per_second": 12.35,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.7251247763633728,
"learning_rate": 4.2e-05,
"loss": 0.0924,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.8,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7659574468085106,
"eval_LOCATION_recall": 0.8372093023255814,
"eval_ORGANIZATION_f1": 0.8602150537634409,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8247422680412371,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.950191570881226,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9323308270676691,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0764974057674408,
"eval_overall_accuracy": 0.9754385964912281,
"eval_overall_f1": 0.8757687576875769,
"eval_overall_precision": 0.8456057007125891,
"eval_overall_recall": 0.9081632653061225,
"eval_runtime": 0.2486,
"eval_samples_per_second": 683.921,
"eval_steps_per_second": 12.069,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.6329052448272705,
"learning_rate": 4.15e-05,
"loss": 0.0914,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.8202247191011235,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7934782608695652,
"eval_LOCATION_recall": 0.8488372093023255,
"eval_ORGANIZATION_f1": 0.8773841961852861,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8518518518518519,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9538461538461539,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9393939393939394,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.07226864248514175,
"eval_overall_accuracy": 0.977327935222672,
"eval_overall_f1": 0.8894409937888199,
"eval_overall_precision": 0.8668280871670703,
"eval_overall_recall": 0.9132653061224489,
"eval_runtime": 0.2471,
"eval_samples_per_second": 687.994,
"eval_steps_per_second": 12.141,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.42153239250183105,
"learning_rate": 4.1e-05,
"loss": 0.0878,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.8156424581005587,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7849462365591398,
"eval_LOCATION_recall": 0.8488372093023255,
"eval_ORGANIZATION_f1": 0.8383561643835616,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8181818181818182,
"eval_ORGANIZATION_recall": 0.8595505617977528,
"eval_PERSON_f1": 0.9612403100775193,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9538461538461539,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.07062693685293198,
"eval_overall_accuracy": 0.9759784075573549,
"eval_overall_f1": 0.8728179551122195,
"eval_overall_precision": 0.8536585365853658,
"eval_overall_recall": 0.8928571428571429,
"eval_runtime": 0.2478,
"eval_samples_per_second": 685.913,
"eval_steps_per_second": 12.104,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.7202361822128296,
"learning_rate": 4.05e-05,
"loss": 0.0838,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.8176795580110496,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7789473684210526,
"eval_LOCATION_recall": 0.8604651162790697,
"eval_ORGANIZATION_f1": 0.8602739726027397,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.839572192513369,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9612403100775193,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9538461538461539,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0692058727145195,
"eval_overall_accuracy": 0.9765182186234818,
"eval_overall_f1": 0.8830845771144279,
"eval_overall_precision": 0.8616504854368932,
"eval_overall_recall": 0.9056122448979592,
"eval_runtime": 0.2474,
"eval_samples_per_second": 687.148,
"eval_steps_per_second": 12.126,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.5943815112113953,
"learning_rate": 4e-05,
"loss": 0.0826,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.8333333333333334,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7978723404255319,
"eval_LOCATION_recall": 0.872093023255814,
"eval_ORGANIZATION_f1": 0.8610354223433241,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8359788359788359,
"eval_ORGANIZATION_recall": 0.8876404494382022,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0661964863538742,
"eval_overall_accuracy": 0.9778677462887989,
"eval_overall_f1": 0.8880597014925373,
"eval_overall_precision": 0.866504854368932,
"eval_overall_recall": 0.9107142857142857,
"eval_runtime": 0.2409,
"eval_samples_per_second": 705.801,
"eval_steps_per_second": 12.455,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 1.0471636056900024,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0783,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.8444444444444444,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8085106382978723,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8698060941828255,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8579234972677595,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0659145712852478,
"eval_overall_accuracy": 0.9784075573549258,
"eval_overall_f1": 0.8947368421052632,
"eval_overall_precision": 0.8793103448275862,
"eval_overall_recall": 0.9107142857142857,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.721,
"eval_steps_per_second": 12.136,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.6707532405853271,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0792,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.8333333333333334,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7978723404255319,
"eval_LOCATION_recall": 0.872093023255814,
"eval_ORGANIZATION_f1": 0.8648648648648649,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8333333333333334,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0643569827079773,
"eval_overall_accuracy": 0.9784075573549258,
"eval_overall_f1": 0.8897149938042132,
"eval_overall_precision": 0.8650602409638555,
"eval_overall_recall": 0.9158163265306123,
"eval_runtime": 0.2486,
"eval_samples_per_second": 683.881,
"eval_steps_per_second": 12.068,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.7425451874732971,
"learning_rate": 3.85e-05,
"loss": 0.0734,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.8508287292817679,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8105263157894737,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8784530386740331,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8641304347826086,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0628323182463646,
"eval_overall_accuracy": 0.9794871794871794,
"eval_overall_f1": 0.9,
"eval_overall_precision": 0.8823529411764706,
"eval_overall_recall": 0.9183673469387755,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.292,
"eval_steps_per_second": 12.164,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.682661771774292,
"learning_rate": 3.8e-05,
"loss": 0.0741,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.8461538461538463,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8020833333333334,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8602739726027397,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.839572192513369,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.06370385736227036,
"eval_overall_accuracy": 0.977327935222672,
"eval_overall_f1": 0.8905472636815919,
"eval_overall_precision": 0.8689320388349514,
"eval_overall_recall": 0.9132653061224489,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.578,
"eval_steps_per_second": 12.098,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 1.4943416118621826,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0704,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8657534246575344,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8449197860962567,
"eval_ORGANIZATION_recall": 0.8876404494382022,
"eval_PERSON_f1": 0.9612403100775193,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9538461538461539,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.06200648099184036,
"eval_overall_accuracy": 0.9784075573549258,
"eval_overall_f1": 0.8941469489414694,
"eval_overall_precision": 0.8734793187347932,
"eval_overall_recall": 0.9158163265306123,
"eval_runtime": 0.2476,
"eval_samples_per_second": 686.7,
"eval_steps_per_second": 12.118,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.677792489528656,
"learning_rate": 3.7e-05,
"loss": 0.0691,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.8508287292817679,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8105263157894737,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.861878453038674,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8478260869565217,
"eval_ORGANIZATION_recall": 0.8764044943820225,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.06109492480754852,
"eval_overall_accuracy": 0.9784075573549258,
"eval_overall_f1": 0.8925000000000001,
"eval_overall_precision": 0.875,
"eval_overall_recall": 0.9107142857142857,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.374,
"eval_steps_per_second": 12.165,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.4048442244529724,
"learning_rate": 3.65e-05,
"loss": 0.0668,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.8351648351648352,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7916666666666666,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8876712328767122,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8663101604278075,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05810139700770378,
"eval_overall_accuracy": 0.979757085020243,
"eval_overall_f1": 0.900497512437811,
"eval_overall_precision": 0.8786407766990292,
"eval_overall_recall": 0.923469387755102,
"eval_runtime": 0.2473,
"eval_samples_per_second": 687.47,
"eval_steps_per_second": 12.132,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 1.1443583965301514,
"learning_rate": 3.6e-05,
"loss": 0.0658,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.8461538461538463,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8020833333333334,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8688524590163934,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8457446808510638,
"eval_ORGANIZATION_recall": 0.8932584269662921,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05813080444931984,
"eval_overall_accuracy": 0.9794871794871794,
"eval_overall_f1": 0.8944099378881987,
"eval_overall_precision": 0.8716707021791767,
"eval_overall_recall": 0.9183673469387755,
"eval_runtime": 0.2486,
"eval_samples_per_second": 683.898,
"eval_steps_per_second": 12.069,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.5618166923522949,
"learning_rate": 3.55e-05,
"loss": 0.0659,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.8603351955307263,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8279569892473119,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8828337874659401,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8571428571428571,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05610692501068115,
"eval_overall_accuracy": 0.9813765182186235,
"eval_overall_f1": 0.9041095890410957,
"eval_overall_precision": 0.8832116788321168,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.374,
"eval_steps_per_second": 12.148,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.3011661171913147,
"learning_rate": 3.5e-05,
"loss": 0.0629,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.8491620111731845,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8172043010752689,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8828337874659401,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8571428571428571,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05478770285844803,
"eval_overall_accuracy": 0.9813765182186235,
"eval_overall_f1": 0.9016189290161892,
"eval_overall_precision": 0.8807785888077859,
"eval_overall_recall": 0.923469387755102,
"eval_runtime": 0.2412,
"eval_samples_per_second": 704.868,
"eval_steps_per_second": 12.439,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.5606756210327148,
"learning_rate": 3.45e-05,
"loss": 0.0606,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.839779005524862,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8698060941828255,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8579234972677595,
"eval_ORGANIZATION_recall": 0.8820224719101124,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.056243132799863815,
"eval_overall_accuracy": 0.9794871794871794,
"eval_overall_f1": 0.8936170212765957,
"eval_overall_precision": 0.8771498771498771,
"eval_overall_recall": 0.9107142857142857,
"eval_runtime": 0.2467,
"eval_samples_per_second": 688.975,
"eval_steps_per_second": 12.158,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.4857378900051117,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0596,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.8369565217391304,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.7857142857142857,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8956043956043956,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8763440860215054,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05502798408269882,
"eval_overall_accuracy": 0.9805668016194332,
"eval_overall_f1": 0.9043478260869564,
"eval_overall_precision": 0.8813559322033898,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2471,
"eval_samples_per_second": 687.899,
"eval_steps_per_second": 12.139,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 1.2027171850204468,
"learning_rate": 3.35e-05,
"loss": 0.0614,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.8444444444444444,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8085106382978723,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8969359331476323,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8895027624309392,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05506258085370064,
"eval_overall_accuracy": 0.9802968960863697,
"eval_overall_f1": 0.907035175879397,
"eval_overall_precision": 0.8935643564356436,
"eval_overall_recall": 0.9209183673469388,
"eval_runtime": 0.2474,
"eval_samples_per_second": 687.153,
"eval_steps_per_second": 12.126,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.4615573287010193,
"learning_rate": 3.3e-05,
"loss": 0.0585,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.8491620111731845,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8172043010752689,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.8956043956043956,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8763440860215054,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05321921035647392,
"eval_overall_accuracy": 0.9816464237516869,
"eval_overall_f1": 0.9075,
"eval_overall_precision": 0.8897058823529411,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.2484,
"eval_samples_per_second": 684.273,
"eval_steps_per_second": 12.075,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.3912416100502014,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0568,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.8508287292817679,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8105263157894737,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8969359331476323,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8895027624309392,
"eval_ORGANIZATION_recall": 0.9044943820224719,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05411427468061447,
"eval_overall_accuracy": 0.9816464237516869,
"eval_overall_f1": 0.9084065244667503,
"eval_overall_precision": 0.8938271604938272,
"eval_overall_recall": 0.923469387755102,
"eval_runtime": 0.2479,
"eval_samples_per_second": 685.845,
"eval_steps_per_second": 12.103,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 1.1017824411392212,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0576,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.8540540540540541,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.797979797979798,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.8870523415977961,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8702702702702703,
"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": 0.05463264510035515,
"eval_overall_accuracy": 0.9802968960863697,
"eval_overall_f1": 0.9079601990049752,
"eval_overall_precision": 0.8859223300970874,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.288,
"eval_steps_per_second": 12.164,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 1.6355993747711182,
"learning_rate": 3.15e-05,
"loss": 0.0554,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.8603351955307263,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8279569892473119,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8975069252077562,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8852459016393442,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.052308570593595505,
"eval_overall_accuracy": 0.9819163292847504,
"eval_overall_f1": 0.9109159347553324,
"eval_overall_precision": 0.8962962962962963,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.2484,
"eval_samples_per_second": 684.473,
"eval_steps_per_second": 12.079,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.5715850591659546,
"learning_rate": 3.1e-05,
"loss": 0.0551,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.8888888888888888,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8791208791208791,
"eval_ORGANIZATION_recall": 0.898876404494382,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.053769923746585846,
"eval_overall_accuracy": 0.9811066126855601,
"eval_overall_f1": 0.9058971141781682,
"eval_overall_precision": 0.891358024691358,
"eval_overall_recall": 0.9209183673469388,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.582,
"eval_steps_per_second": 12.099,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.3516031801700592,
"learning_rate": 3.05e-05,
"loss": 0.0514,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.8571428571428572,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8125,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.913649025069638,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9060773480662984,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.052653856575489044,
"eval_overall_accuracy": 0.9819163292847504,
"eval_overall_f1": 0.9172932330827067,
"eval_overall_precision": 0.9014778325123153,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.597,
"eval_steps_per_second": 12.099,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.7315645813941956,
"learning_rate": 3e-05,
"loss": 0.0536,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.861878453038674,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8210526315789474,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.902506963788301,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8950276243093923,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0524393655359745,
"eval_overall_accuracy": 0.9819163292847504,
"eval_overall_f1": 0.9134253450439147,
"eval_overall_precision": 0.8987654320987655,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2456,
"eval_samples_per_second": 692.163,
"eval_steps_per_second": 12.215,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.2149118036031723,
"learning_rate": 2.95e-05,
"loss": 0.0514,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.8508287292817679,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8105263157894737,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9055555555555556,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8956043956043956,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.05115543678402901,
"eval_overall_accuracy": 0.9821862348178138,
"eval_overall_f1": 0.9134253450439147,
"eval_overall_precision": 0.8987654320987655,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2475,
"eval_samples_per_second": 686.844,
"eval_steps_per_second": 12.121,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.7280898690223694,
"learning_rate": 2.9e-05,
"loss": 0.0503,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9095890410958904,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8877005347593583,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.048962149769067764,
"eval_overall_accuracy": 0.9824561403508771,
"eval_overall_f1": 0.916354556803995,
"eval_overall_precision": 0.8973105134474327,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2482,
"eval_samples_per_second": 684.906,
"eval_steps_per_second": 12.087,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.3854430913925171,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0512,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.8791208791208791,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9141274238227147,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9016393442622951,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04967450350522995,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9236545682102628,
"eval_overall_precision": 0.9066339066339066,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2481,
"eval_samples_per_second": 685.339,
"eval_steps_per_second": 12.094,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.5250909328460693,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.051,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.8839779005524862,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8421052631578947,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9116022099447514,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8967391304347826,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.049224358052015305,
"eval_overall_accuracy": 0.9832658569500675,
"eval_overall_f1": 0.9236545682102628,
"eval_overall_precision": 0.9066339066339066,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2468,
"eval_samples_per_second": 688.872,
"eval_steps_per_second": 12.157,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.759871780872345,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0489,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9055555555555556,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8956043956043956,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.049404654651880264,
"eval_overall_accuracy": 0.9821862348178138,
"eval_overall_f1": 0.914572864321608,
"eval_overall_precision": 0.900990099009901,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.15,
"eval_steps_per_second": 12.144,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 1.2708690166473389,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.05,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.8804347826086957,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.826530612244898,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9085872576177285,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8961748633879781,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0508941188454628,
"eval_overall_accuracy": 0.9821862348178138,
"eval_overall_f1": 0.9213483146067415,
"eval_overall_precision": 0.902200488997555,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.582,
"eval_steps_per_second": 12.099,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.533057451248169,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0473,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9196675900277007,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.907103825136612,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04795275256037712,
"eval_overall_accuracy": 0.9827260458839406,
"eval_overall_f1": 0.9209535759096613,
"eval_overall_precision": 0.9061728395061729,
"eval_overall_recall": 0.9362244897959183,
"eval_runtime": 0.2471,
"eval_samples_per_second": 688.004,
"eval_steps_per_second": 12.141,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.7810581922531128,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0454,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.8555555555555555,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8191489361702128,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9192200557103065,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9116022099447514,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04894954338669777,
"eval_overall_accuracy": 0.9827260458839406,
"eval_overall_f1": 0.9207547169811321,
"eval_overall_precision": 0.9081885856079405,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2476,
"eval_samples_per_second": 686.586,
"eval_steps_per_second": 12.116,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.36862263083457947,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0468,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.8571428571428572,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8125,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.9101123595505618,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9101123595505618,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.049755748361349106,
"eval_overall_accuracy": 0.9835357624831309,
"eval_overall_f1": 0.9168765743073048,
"eval_overall_precision": 0.9054726368159204,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.67,
"eval_steps_per_second": 12.135,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.5205909013748169,
"learning_rate": 2.5e-05,
"loss": 0.044,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.8508287292817679,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8105263157894737,
"eval_LOCATION_recall": 0.8953488372093024,
"eval_ORGANIZATION_f1": 0.9080779944289694,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9005524861878453,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04883972555398941,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.914572864321608,
"eval_overall_precision": 0.900990099009901,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2408,
"eval_samples_per_second": 705.878,
"eval_steps_per_second": 12.457,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.37087270617485046,
"learning_rate": 2.45e-05,
"loss": 0.0439,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.8950276243093923,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8526315789473684,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.049540888518095016,
"eval_overall_accuracy": 0.9835357624831309,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9135802469135802,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2476,
"eval_samples_per_second": 686.661,
"eval_steps_per_second": 12.118,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.4958249628543854,
"learning_rate": 2.4e-05,
"loss": 0.0451,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.8491620111731845,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8172043010752689,
"eval_LOCATION_recall": 0.8837209302325582,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04900331422686577,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9166666666666666,
"eval_overall_precision": 0.9075,
"eval_overall_recall": 0.9260204081632653,
"eval_runtime": 0.2461,
"eval_samples_per_second": 690.67,
"eval_steps_per_second": 12.188,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.5232071876525879,
"learning_rate": 2.35e-05,
"loss": 0.0438,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.8852459016393444,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8350515463917526,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9080779944289694,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9005524861878453,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.049120884388685226,
"eval_overall_accuracy": 0.9827260458839406,
"eval_overall_f1": 0.9223057644110276,
"eval_overall_precision": 0.9064039408866995,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.37,
"eval_steps_per_second": 12.148,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 1.0911372900009155,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0433,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.8715083798882681,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8387096774193549,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.9222222222222223,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9120879120879121,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.046406690031290054,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9257861635220126,
"eval_overall_precision": 0.913151364764268,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.619,
"eval_steps_per_second": 12.099,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.46358591318130493,
"learning_rate": 2.25e-05,
"loss": 0.0441,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.8791208791208791,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9116022099447514,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8967391304347826,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04767988994717598,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9225,
"eval_overall_precision": 0.9044117647058824,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2473,
"eval_samples_per_second": 687.554,
"eval_steps_per_second": 12.133,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.8193870186805725,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0441,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.8791208791208791,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9090909090909092,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8918918918918919,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.046976424753665924,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9213483146067415,
"eval_overall_precision": 0.902200488997555,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2467,
"eval_samples_per_second": 689.223,
"eval_steps_per_second": 12.163,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.5477964878082275,
"learning_rate": 2.15e-05,
"loss": 0.0419,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.8961748633879781,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.845360824742268,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9065934065934066,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8870967741935484,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.046787720173597336,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9240348692403487,
"eval_overall_precision": 0.902676399026764,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2468,
"eval_samples_per_second": 688.842,
"eval_steps_per_second": 12.156,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.3520606756210327,
"learning_rate": 2.1e-05,
"loss": 0.0421,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.8729281767955801,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8315789473684211,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9101123595505618,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9101123595505618,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04738873988389969,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9205548549810846,
"eval_overall_precision": 0.9102244389027432,
"eval_overall_recall": 0.9311224489795918,
"eval_runtime": 0.2473,
"eval_samples_per_second": 687.386,
"eval_steps_per_second": 12.13,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.5022946000099182,
"learning_rate": 2.05e-05,
"loss": 0.0385,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.8666666666666666,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8297872340425532,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.907563025210084,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9050279329608939,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0471520870923996,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9180327868852458,
"eval_overall_precision": 0.9077306733167082,
"eval_overall_recall": 0.9285714285714286,
"eval_runtime": 0.2486,
"eval_samples_per_second": 683.966,
"eval_steps_per_second": 12.07,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.9798009395599365,
"learning_rate": 2e-05,
"loss": 0.0424,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.8666666666666666,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8297872340425532,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.9111111111111112,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9010989010989011,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0452764555811882,
"eval_overall_accuracy": 0.9838056680161943,
"eval_overall_f1": 0.9195979899497488,
"eval_overall_precision": 0.905940594059406,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2471,
"eval_samples_per_second": 687.917,
"eval_steps_per_second": 12.14,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.5093074440956116,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0399,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.8777777777777779,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8404255319148937,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9090909090909092,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8918918918918919,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.044645652174949646,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9211514392991239,
"eval_overall_precision": 0.9041769041769042,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.418,
"eval_steps_per_second": 12.096,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.4424732029438019,
"learning_rate": 1.9e-05,
"loss": 0.0393,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.8839779005524862,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8421052631578947,
"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": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04541868716478348,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9207547169811321,
"eval_overall_precision": 0.9081885856079405,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2477,
"eval_samples_per_second": 686.337,
"eval_steps_per_second": 12.112,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 1.917741060256958,
"learning_rate": 1.85e-05,
"loss": 0.0386,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.8961748633879781,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.845360824742268,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9116022099447514,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8967391304347826,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04548858851194382,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9263420724094882,
"eval_overall_precision": 0.9070904645476773,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2468,
"eval_samples_per_second": 688.821,
"eval_steps_per_second": 12.156,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.2670099437236786,
"learning_rate": 1.8e-05,
"loss": 0.0386,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.8715083798882681,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8387096774193549,
"eval_LOCATION_recall": 0.9069767441860465,
"eval_ORGANIZATION_f1": 0.901098901098901,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8817204301075269,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04432997852563858,
"eval_overall_accuracy": 0.9843454790823212,
"eval_overall_f1": 0.916145181476846,
"eval_overall_precision": 0.8992628992628993,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2474,
"eval_samples_per_second": 687.128,
"eval_steps_per_second": 12.126,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.15305323898792267,
"learning_rate": 1.75e-05,
"loss": 0.0378,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.8852459016393444,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8350515463917526,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9146005509641874,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.8972972972972973,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04566904902458191,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9251870324189526,
"eval_overall_precision": 0.9048780487804878,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.317,
"eval_steps_per_second": 12.147,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.5877130031585693,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0376,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.8839779005524862,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8421052631578947,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04576703533530235,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9259723964868256,
"eval_overall_precision": 0.9111111111111111,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2476,
"eval_samples_per_second": 686.688,
"eval_steps_per_second": 12.118,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.2808298170566559,
"learning_rate": 1.65e-05,
"loss": 0.0362,
"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": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045613568276166916,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9259723964868256,
"eval_overall_precision": 0.9111111111111111,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.647,
"eval_steps_per_second": 12.135,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.922883152961731,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0366,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.8999999999999999,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8617021276595744,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9111111111111112,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9010989010989011,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04581554979085922,
"eval_overall_accuracy": 0.9840755735492578,
"eval_overall_f1": 0.9271356783919599,
"eval_overall_precision": 0.9133663366336634,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.199,
"eval_steps_per_second": 12.392,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 1.1859774589538574,
"learning_rate": 1.55e-05,
"loss": 0.038,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.8999999999999999,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8617021276595744,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9187675070028011,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9162011173184358,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045918650925159454,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9201995012468828,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2463,
"eval_samples_per_second": 690.082,
"eval_steps_per_second": 12.178,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.33540353178977966,
"learning_rate": 1.5e-05,
"loss": 0.0364,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.8950276243093923,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8526315789473684,
"eval_LOCATION_recall": 0.9418604651162791,
"eval_ORGANIZATION_f1": 0.9141274238227147,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9016393442622951,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045043688267469406,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9273182957393483,
"eval_overall_precision": 0.9113300492610837,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.348,
"eval_steps_per_second": 12.165,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 1.4105803966522217,
"learning_rate": 1.45e-05,
"loss": 0.0361,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9171270718232043,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9021739130434783,
"eval_ORGANIZATION_recall": 0.9325842696629213,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04533083364367485,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9323308270676692,
"eval_overall_precision": 0.916256157635468,
"eval_overall_recall": 0.9489795918367347,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.264,
"eval_steps_per_second": 12.146,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.2059611678123474,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0358,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9050279329608939,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.9101123595505618,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04745972529053688,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9246231155778896,
"eval_overall_precision": 0.9108910891089109,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.439,
"eval_steps_per_second": 12.167,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.6744855642318726,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0356,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.8729281767955801,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8315789473684211,
"eval_LOCATION_recall": 0.9186046511627907,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04626096412539482,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9219143576826196,
"eval_overall_precision": 0.9104477611940298,
"eval_overall_recall": 0.9336734693877551,
"eval_runtime": 0.2477,
"eval_samples_per_second": 686.23,
"eval_steps_per_second": 12.11,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.9891471862792969,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0366,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04604022204875946,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9201995012468828,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.802,
"eval_steps_per_second": 12.138,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.6050940155982971,
"learning_rate": 1.25e-05,
"loss": 0.0345,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9010989010989011,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8541666666666666,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.913649025069638,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9060773480662984,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045599959790706635,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9135802469135802,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2478,
"eval_samples_per_second": 686.13,
"eval_steps_per_second": 12.108,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.571677565574646,
"learning_rate": 1.2e-05,
"loss": 0.0352,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.8791208791208791,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9302325581395349,
"eval_ORGANIZATION_f1": 0.913649025069638,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9060773480662984,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04553736373782158,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9234629861982434,
"eval_overall_precision": 0.908641975308642,
"eval_overall_recall": 0.9387755102040817,
"eval_runtime": 0.247,
"eval_samples_per_second": 688.301,
"eval_steps_per_second": 12.146,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.24387818574905396,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0344,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.044447530061006546,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9183168316831684,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.386,
"eval_steps_per_second": 12.166,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 1.053953766822815,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0364,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.913649025069638,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9060773480662984,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04617859423160553,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9158415841584159,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2469,
"eval_samples_per_second": 688.621,
"eval_steps_per_second": 12.152,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.9294384121894836,
"learning_rate": 1.05e-05,
"loss": 0.0351,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9171270718232045,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8736842105263158,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04505502060055733,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9185185185185185,
"eval_overall_recall": 0.9489795918367347,
"eval_runtime": 0.2463,
"eval_samples_per_second": 690.079,
"eval_steps_per_second": 12.178,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.6035823225975037,
"learning_rate": 1e-05,
"loss": 0.0359,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9171270718232045,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8736842105263158,
"eval_LOCATION_recall": 0.9651162790697675,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04532361403107643,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9185185185185185,
"eval_overall_recall": 0.9489795918367347,
"eval_runtime": 0.248,
"eval_samples_per_second": 685.369,
"eval_steps_per_second": 12.095,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.28479549288749695,
"learning_rate": 9.5e-06,
"loss": 0.0338,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9010989010989011,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8541666666666666,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04476336017251015,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9137931034482759,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2475,
"eval_samples_per_second": 686.989,
"eval_steps_per_second": 12.123,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.9992564916610718,
"learning_rate": 9e-06,
"loss": 0.0349,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"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": 0.9649805447470817,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.9612403100775194,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045466963201761246,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9271356783919599,
"eval_overall_precision": 0.9133663366336634,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.457,
"eval_steps_per_second": 12.432,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 1.1618850231170654,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0346,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.044760651886463165,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9183168316831684,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2467,
"eval_samples_per_second": 689.16,
"eval_steps_per_second": 12.162,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.4722515046596527,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0339,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.913649025069638,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9060773480662984,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04559604451060295,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9158415841584159,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2467,
"eval_samples_per_second": 689.154,
"eval_steps_per_second": 12.162,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 1.2708790302276611,
"learning_rate": 7.5e-06,
"loss": 0.0336,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04564376920461655,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9319899244332494,
"eval_overall_precision": 0.9203980099502488,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2464,
"eval_samples_per_second": 690.053,
"eval_steps_per_second": 12.177,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.12567788362503052,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0333,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04525807872414589,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9160493827160494,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2464,
"eval_samples_per_second": 689.925,
"eval_steps_per_second": 12.175,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.4181559383869171,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0354,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045248523354530334,
"eval_overall_accuracy": 0.9846153846153847,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9201995012468828,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2466,
"eval_samples_per_second": 689.498,
"eval_steps_per_second": 12.168,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 1.1250125169754028,
"learning_rate": 6e-06,
"loss": 0.0348,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04508548229932785,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9183168316831684,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2467,
"eval_samples_per_second": 689.165,
"eval_steps_per_second": 12.162,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.16692405939102173,
"learning_rate": 5.500000000000001e-06,
"loss": 0.034,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.044971730560064316,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9183168316831684,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.735,
"eval_steps_per_second": 12.136,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.5090487599372864,
"learning_rate": 5e-06,
"loss": 0.0337,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04512477666139603,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9160493827160494,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2471,
"eval_samples_per_second": 687.97,
"eval_steps_per_second": 12.141,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.8777878284454346,
"learning_rate": 4.5e-06,
"loss": 0.0325,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04508595168590546,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9318181818181819,
"eval_overall_precision": 0.9225,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2477,
"eval_samples_per_second": 686.416,
"eval_steps_per_second": 12.113,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.25065359473228455,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0325,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9131652661064427,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9106145251396648,
"eval_ORGANIZATION_recall": 0.9157303370786517,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0452127642929554,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9318181818181819,
"eval_overall_precision": 0.9225,
"eval_overall_recall": 0.9413265306122449,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.826,
"eval_steps_per_second": 12.138,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.6787272095680237,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0342,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9166666666666666,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9065934065934066,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.044928453862667084,
"eval_overall_accuracy": 0.9848852901484481,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9160493827160494,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2473,
"eval_samples_per_second": 687.294,
"eval_steps_per_second": 12.129,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.2792554795742035,
"learning_rate": 3e-06,
"loss": 0.0321,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04493473097681999,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9331651954602775,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2471,
"eval_samples_per_second": 688.06,
"eval_steps_per_second": 12.142,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.6919907331466675,
"learning_rate": 2.5e-06,
"loss": 0.0335,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9162011173184358,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8817204301075269,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.0449887178838253,
"eval_overall_accuracy": 0.9856950067476383,
"eval_overall_f1": 0.9331651954602775,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2469,
"eval_samples_per_second": 688.525,
"eval_steps_per_second": 12.15,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.3126802444458008,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.033,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045047108083963394,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9319899244332494,
"eval_overall_precision": 0.9203980099502488,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2475,
"eval_samples_per_second": 686.812,
"eval_steps_per_second": 12.12,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.14203719794750214,
"learning_rate": 1.5e-06,
"loss": 0.0322,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9111111111111112,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8723404255319149,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.045190200209617615,
"eval_overall_accuracy": 0.9854251012145749,
"eval_overall_f1": 0.9319899244332494,
"eval_overall_precision": 0.9203980099502488,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2472,
"eval_samples_per_second": 687.789,
"eval_steps_per_second": 12.137,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 1.7554861307144165,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0333,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9192200557103065,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9116022099447514,
"eval_ORGANIZATION_recall": 0.9269662921348315,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04513276740908623,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9183168316831684,
"eval_overall_recall": 0.9464285714285714,
"eval_runtime": 0.2464,
"eval_samples_per_second": 690.066,
"eval_steps_per_second": 12.178,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.3359507918357849,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0317,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04522684961557388,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9308176100628932,
"eval_overall_precision": 0.9181141439205955,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2467,
"eval_samples_per_second": 689.109,
"eval_steps_per_second": 12.161,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.5259885191917419,
"learning_rate": 0.0,
"loss": 0.0332,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9060773480662985,
"eval_LOCATION_number": 86,
"eval_LOCATION_precision": 0.8631578947368421,
"eval_LOCATION_recall": 0.9534883720930233,
"eval_ORGANIZATION_f1": 0.9162011173184358,
"eval_ORGANIZATION_number": 178,
"eval_ORGANIZATION_precision": 0.9111111111111111,
"eval_ORGANIZATION_recall": 0.9213483146067416,
"eval_PERSON_f1": 0.96875,
"eval_PERSON_number": 128,
"eval_PERSON_precision": 0.96875,
"eval_PERSON_recall": 0.96875,
"eval_loss": 0.04522377625107765,
"eval_overall_accuracy": 0.9851551956815114,
"eval_overall_f1": 0.9308176100628932,
"eval_overall_precision": 0.9181141439205955,
"eval_overall_recall": 0.9438775510204082,
"eval_runtime": 0.2473,
"eval_samples_per_second": 687.439,
"eval_steps_per_second": 12.131,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 3878410539426276.0,
"train_loss": 0.08344241137305895,
"train_runtime": 566.812,
"train_samples_per_second": 270.107,
"train_steps_per_second": 16.937
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 3878410539426276.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}