nerui-pt-pl30-0 / trainer_state.json
apwic's picture
End of training
432bc08 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": 0.9950183629989624,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8686,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.0,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.0,
"eval_LOCATION_recall": 0.0,
"eval_ORGANIZATION_f1": 0.18497109826589597,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.1787709497206704,
"eval_ORGANIZATION_recall": 0.19161676646706588,
"eval_PERSON_f1": 0.2823529411764706,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.23645320197044334,
"eval_PERSON_recall": 0.35036496350364965,
"eval_loss": 0.41679391264915466,
"eval_overall_accuracy": 0.8588397790055249,
"eval_overall_f1": 0.20460358056265984,
"eval_overall_precision": 0.20833333333333334,
"eval_overall_recall": 0.20100502512562815,
"eval_runtime": 0.2977,
"eval_samples_per_second": 571.08,
"eval_steps_per_second": 10.078,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.8621328473091125,
"learning_rate": 4.9e-05,
"loss": 0.3777,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.38461538461538464,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.4838709677419355,
"eval_LOCATION_recall": 0.3191489361702128,
"eval_ORGANIZATION_f1": 0.5449999999999999,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.4678111587982833,
"eval_ORGANIZATION_recall": 0.6526946107784432,
"eval_PERSON_f1": 0.7161290322580646,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.6416184971098265,
"eval_PERSON_recall": 0.8102189781021898,
"eval_loss": 0.2543336749076843,
"eval_overall_accuracy": 0.9215469613259668,
"eval_overall_f1": 0.5773672055427252,
"eval_overall_precision": 0.5341880341880342,
"eval_overall_recall": 0.628140703517588,
"eval_runtime": 0.2972,
"eval_samples_per_second": 571.967,
"eval_steps_per_second": 10.094,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 1.0228835344314575,
"learning_rate": 4.85e-05,
"loss": 0.2087,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7777777777777779,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7403846153846154,
"eval_LOCATION_recall": 0.8191489361702128,
"eval_ORGANIZATION_f1": 0.7507002801120449,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.7052631578947368,
"eval_ORGANIZATION_recall": 0.8023952095808383,
"eval_PERSON_f1": 0.9503546099290779,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9241379310344827,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.11497737467288971,
"eval_overall_accuracy": 0.9651933701657458,
"eval_overall_f1": 0.8243727598566307,
"eval_overall_precision": 0.785876993166287,
"eval_overall_recall": 0.8668341708542714,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.129,
"eval_steps_per_second": 10.202,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.7725925445556641,
"learning_rate": 4.8e-05,
"loss": 0.1366,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8173076923076923,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7456140350877193,
"eval_LOCATION_recall": 0.9042553191489362,
"eval_ORGANIZATION_f1": 0.7461773700305809,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.7625,
"eval_ORGANIZATION_recall": 0.7305389221556886,
"eval_PERSON_f1": 0.96113074204947,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9315068493150684,
"eval_PERSON_recall": 0.9927007299270073,
"eval_loss": 0.09076467156410217,
"eval_overall_accuracy": 0.969060773480663,
"eval_overall_f1": 0.8386308068459658,
"eval_overall_precision": 0.8166666666666667,
"eval_overall_recall": 0.8618090452261307,
"eval_runtime": 0.2958,
"eval_samples_per_second": 574.711,
"eval_steps_per_second": 10.142,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.665722131729126,
"learning_rate": 4.75e-05,
"loss": 0.116,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8911917098445595,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8686868686868687,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.809667673716012,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8170731707317073,
"eval_ORGANIZATION_recall": 0.8023952095808383,
"eval_PERSON_f1": 0.9677419354838709,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9507042253521126,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.07181097567081451,
"eval_overall_accuracy": 0.9759668508287292,
"eval_overall_f1": 0.8841843088418431,
"eval_overall_precision": 0.8765432098765432,
"eval_overall_recall": 0.8919597989949749,
"eval_runtime": 0.2964,
"eval_samples_per_second": 573.644,
"eval_steps_per_second": 10.123,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.580788791179657,
"learning_rate": 4.7e-05,
"loss": 0.0965,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.9,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8490566037735849,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8658536585365854,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8819875776397516,
"eval_ORGANIZATION_recall": 0.8502994011976048,
"eval_PERSON_f1": 0.9818181818181817,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9782608695652174,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.054434362798929214,
"eval_overall_accuracy": 0.9809392265193371,
"eval_overall_f1": 0.9140722291407224,
"eval_overall_precision": 0.9061728395061729,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.821,
"eval_steps_per_second": 10.197,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.7797803282737732,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0853,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.875,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7982456140350878,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8545454545454545,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8650306748466258,
"eval_ORGANIZATION_recall": 0.844311377245509,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05327123776078224,
"eval_overall_accuracy": 0.9809392265193371,
"eval_overall_f1": 0.9037037037037038,
"eval_overall_precision": 0.8883495145631068,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2936,
"eval_samples_per_second": 578.949,
"eval_steps_per_second": 10.217,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.3263556659221649,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0797,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.91,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8584905660377359,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8682634730538922,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8682634730538922,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.046990904957056046,
"eval_overall_accuracy": 0.9839779005524862,
"eval_overall_f1": 0.9169764560099132,
"eval_overall_precision": 0.9046454767726161,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.826,
"eval_steps_per_second": 10.162,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.439500629901886,
"learning_rate": 4.55e-05,
"loss": 0.0702,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.8952380952380952,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8103448275862069,
"eval_LOCATION_recall": 1.0,
"eval_ORGANIZATION_f1": 0.8722741433021806,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9090909090909091,
"eval_ORGANIZATION_recall": 0.8383233532934131,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04428368806838989,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.917910447761194,
"eval_overall_precision": 0.9088669950738916,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.296,
"eval_samples_per_second": 574.293,
"eval_steps_per_second": 10.135,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.9789717197418213,
"learning_rate": 4.5e-05,
"loss": 0.07,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.968421052631579,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9583333333333334,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9106628242074927,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8777777777777778,
"eval_ORGANIZATION_recall": 0.9461077844311377,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.03766591101884842,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9494451294697904,
"eval_overall_precision": 0.9322033898305084,
"eval_overall_recall": 0.9673366834170855,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.843,
"eval_steps_per_second": 10.162,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.6554816365242004,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.063,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9387755102040817,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9019607843137255,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.034425150603055954,
"eval_overall_accuracy": 0.9897790055248619,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.044,
"eval_steps_per_second": 10.148,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.21946755051612854,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0565,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9238578680203046,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.883495145631068,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8988095238095238,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.893491124260355,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04345344752073288,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9316770186335404,
"eval_overall_precision": 0.9213759213759214,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.355,
"eval_steps_per_second": 10.171,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.6675106287002563,
"learning_rate": 4.35e-05,
"loss": 0.056,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9292929292929293,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8846153846153846,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9012345679012346,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.03897729143500328,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.722,
"eval_steps_per_second": 10.16,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.4662700593471527,
"learning_rate": 4.3e-05,
"loss": 0.0516,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.93,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8773584905660378,
"eval_LOCATION_recall": 0.9893617021276596,
"eval_ORGANIZATION_f1": 0.8990825688073394,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.91875,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.0420953743159771,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9313358302122346,
"eval_overall_precision": 0.9255583126550868,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.3034,
"eval_samples_per_second": 560.371,
"eval_steps_per_second": 9.889,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.5384670495986938,
"learning_rate": 4.25e-05,
"loss": 0.0485,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9424083769633509,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9278350515463918,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9266862170087976,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9080459770114943,
"eval_ORGANIZATION_recall": 0.9461077844311377,
"eval_PERSON_f1": 0.9745454545454545,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9710144927536232,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.033467479050159454,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9467162329615861,
"eval_overall_precision": 0.9339853300733496,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2992,
"eval_samples_per_second": 568.154,
"eval_steps_per_second": 10.026,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.528849720954895,
"learning_rate": 4.2e-05,
"loss": 0.046,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9447236180904524,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8952380952380953,
"eval_LOCATION_recall": 1.0,
"eval_ORGANIZATION_f1": 0.9226006191950465,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9551282051282052,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.035197723656892776,
"eval_overall_accuracy": 0.9895027624309393,
"eval_overall_f1": 0.9484276729559749,
"eval_overall_precision": 0.9496221662468514,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2924,
"eval_samples_per_second": 581.371,
"eval_steps_per_second": 10.259,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.6038524508476257,
"learning_rate": 4.15e-05,
"loss": 0.0448,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.934010152284264,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8932038834951457,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9018404907975461,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9245283018867925,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.037710756063461304,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9371859296482412,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2938,
"eval_samples_per_second": 578.575,
"eval_steps_per_second": 10.21,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.47480639815330505,
"learning_rate": 4.1e-05,
"loss": 0.0409,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.8878048780487804,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8198198198198198,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8910256410256411,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9586206896551724,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05055383965373039,
"eval_overall_accuracy": 0.9834254143646409,
"eval_overall_f1": 0.920353982300885,
"eval_overall_precision": 0.926208651399491,
"eval_overall_recall": 0.914572864321608,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.365,
"eval_steps_per_second": 10.224,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 1.3145582675933838,
"learning_rate": 4.05e-05,
"loss": 0.0376,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9353846153846154,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9620253164556962,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.03691571578383446,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9508196721311476,
"eval_overall_precision": 0.9544303797468354,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2954,
"eval_samples_per_second": 575.466,
"eval_steps_per_second": 10.155,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.9411401152610779,
"learning_rate": 4e-05,
"loss": 0.0382,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9009900990099009,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8425925925925926,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9493670886075949,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04132825508713722,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2955,
"eval_samples_per_second": 575.326,
"eval_steps_per_second": 10.153,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.6504610180854797,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0364,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.900990099009901,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9272727272727274,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.03534973785281181,
"eval_overall_accuracy": 0.9895027624309393,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.624,
"eval_steps_per_second": 10.176,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.2652185261249542,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.036,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.934010152284264,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8932038834951457,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9216867469879517,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.03927252069115639,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.629,
"eval_steps_per_second": 10.193,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.26572874188423157,
"learning_rate": 3.85e-05,
"loss": 0.0356,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9187500000000001,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9607843137254902,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.045102085918188095,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.943109987357775,
"eval_overall_precision": 0.9491094147582697,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.812,
"eval_steps_per_second": 10.161,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.3797498047351837,
"learning_rate": 3.8e-05,
"loss": 0.0322,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9268292682926829,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9440993788819876,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.039436403661966324,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9472361809045227,
"eval_overall_precision": 0.9472361809045227,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.596,
"eval_steps_per_second": 10.175,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.6956537961959839,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0342,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9064327485380117,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.041248563677072525,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9416149068322981,
"eval_overall_precision": 0.9312039312039312,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.296,
"eval_samples_per_second": 574.277,
"eval_steps_per_second": 10.134,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.5702881217002869,
"learning_rate": 3.7e-05,
"loss": 0.0309,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9238578680203046,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.883495145631068,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04878287762403488,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.757,
"eval_steps_per_second": 10.16,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.7046517133712769,
"learning_rate": 3.65e-05,
"loss": 0.0282,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9381443298969071,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.91,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.03887735679745674,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2946,
"eval_samples_per_second": 576.962,
"eval_steps_per_second": 10.182,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.28707966208457947,
"learning_rate": 3.6e-05,
"loss": 0.0267,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9009900990099009,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8425925925925926,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04715035483241081,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9339975093399752,
"eval_overall_precision": 0.9259259259259259,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2935,
"eval_samples_per_second": 579.135,
"eval_steps_per_second": 10.22,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.4028223156929016,
"learning_rate": 3.55e-05,
"loss": 0.0298,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.91,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8584905660377359,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9107692307692307,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.042759254574775696,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2925,
"eval_samples_per_second": 581.141,
"eval_steps_per_second": 10.255,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.46693184971809387,
"learning_rate": 3.5e-05,
"loss": 0.0262,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9238578680203046,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.883495145631068,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9337349397590362,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04283633455634117,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2966,
"eval_samples_per_second": 573.104,
"eval_steps_per_second": 10.114,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.2504064738750458,
"learning_rate": 3.45e-05,
"loss": 0.0273,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.934010152284264,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8932038834951457,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.042587727308273315,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9461827284105131,
"eval_overall_precision": 0.942643391521197,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2954,
"eval_samples_per_second": 575.486,
"eval_steps_per_second": 10.156,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 1.111054539680481,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0253,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9003021148036255,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9085365853658537,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.045077793300151825,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9338327091136079,
"eval_overall_precision": 0.9280397022332506,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2953,
"eval_samples_per_second": 575.632,
"eval_steps_per_second": 10.158,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.5728123188018799,
"learning_rate": 3.35e-05,
"loss": 0.0265,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8882175226586103,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8963414634146342,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.052353814244270325,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9226932668329177,
"eval_overall_precision": 0.9158415841584159,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.768,
"eval_steps_per_second": 10.196,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.6091629266738892,
"learning_rate": 3.3e-05,
"loss": 0.0236,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.047763314098119736,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9333333333333332,
"eval_overall_precision": 0.9345088161209067,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.296,
"eval_samples_per_second": 574.251,
"eval_steps_per_second": 10.134,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.10599525272846222,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0207,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9272727272727274,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04899630323052406,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.949748743718593,
"eval_overall_precision": 0.949748743718593,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.087,
"eval_steps_per_second": 10.149,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.6369150280952454,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0208,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.043838970363140106,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9411764705882354,
"eval_overall_precision": 0.9376558603491272,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2929,
"eval_samples_per_second": 580.307,
"eval_steps_per_second": 10.241,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.5807005763053894,
"learning_rate": 3.15e-05,
"loss": 0.0217,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9145728643216081,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8666666666666667,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04792096093297005,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9391304347826087,
"eval_overall_precision": 0.9287469287469288,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2979,
"eval_samples_per_second": 570.621,
"eval_steps_per_second": 10.07,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.9765740633010864,
"learning_rate": 3.1e-05,
"loss": 0.0205,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9341317365269461,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9341317365269461,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04430354759097099,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.951310861423221,
"eval_overall_precision": 0.9454094292803971,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2957,
"eval_samples_per_second": 574.821,
"eval_steps_per_second": 10.144,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.41134005784988403,
"learning_rate": 3.05e-05,
"loss": 0.02,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04428057000041008,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9411764705882354,
"eval_overall_precision": 0.9376558603491272,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2955,
"eval_samples_per_second": 575.293,
"eval_steps_per_second": 10.152,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.2633439600467682,
"learning_rate": 3e-05,
"loss": 0.0196,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9381443298969071,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.91,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9244712990936556,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.03948396071791649,
"eval_overall_accuracy": 0.9900552486187846,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2959,
"eval_samples_per_second": 574.497,
"eval_steps_per_second": 10.138,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.2167958766222,
"learning_rate": 2.95e-05,
"loss": 0.0193,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9238578680203046,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.883495145631068,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04814286530017853,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2928,
"eval_samples_per_second": 580.69,
"eval_steps_per_second": 10.247,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.3106689751148224,
"learning_rate": 2.9e-05,
"loss": 0.0192,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.900990099009901,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9337349397590362,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04553689435124397,
"eval_overall_accuracy": 0.9895027624309393,
"eval_overall_f1": 0.9525,
"eval_overall_precision": 0.9477611940298507,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.664,
"eval_steps_per_second": 10.229,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.6286072134971619,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.018,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9235474006116209,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.053353674709796906,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9447236180904522,
"eval_overall_precision": 0.9447236180904522,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2972,
"eval_samples_per_second": 572.031,
"eval_steps_per_second": 10.095,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.43395888805389404,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0177,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.91,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8584905660377359,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9235474006116209,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05498238652944565,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2961,
"eval_samples_per_second": 574.04,
"eval_steps_per_second": 10.13,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.06477583199739456,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0169,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04276302456855774,
"eval_overall_accuracy": 0.9895027624309393,
"eval_overall_f1": 0.9398496240601504,
"eval_overall_precision": 0.9375,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2975,
"eval_samples_per_second": 571.414,
"eval_steps_per_second": 10.084,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.28106066584587097,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0171,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.042081184685230255,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.286,
"eval_steps_per_second": 10.187,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.56827712059021,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0165,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.045455124229192734,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2988,
"eval_samples_per_second": 568.94,
"eval_steps_per_second": 10.04,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.513745129108429,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0149,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8948948948948949,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8975903614457831,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05499190092086792,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9240348692403487,
"eval_overall_precision": 0.9160493827160494,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.205,
"eval_steps_per_second": 10.186,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.07015065103769302,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0164,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05658362805843353,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.82,
"eval_steps_per_second": 10.197,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.5518860220909119,
"learning_rate": 2.5e-05,
"loss": 0.015,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.8923076923076922,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8613861386138614,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05521540343761444,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9275,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2931,
"eval_samples_per_second": 580.104,
"eval_steps_per_second": 10.237,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.0402052104473114,
"learning_rate": 2.45e-05,
"loss": 0.0152,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.905775075987842,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05571586266160011,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9286608260325407,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2969,
"eval_samples_per_second": 572.671,
"eval_steps_per_second": 10.106,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.06455733627080917,
"learning_rate": 2.4e-05,
"loss": 0.0155,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.8969072164948454,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.87,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04739854484796524,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9398496240601504,
"eval_overall_precision": 0.9375,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.789,
"eval_steps_per_second": 10.179,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.9167325496673584,
"learning_rate": 2.35e-05,
"loss": 0.0155,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9268292682926829,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9440993788819876,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.050272900611162186,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9422110552763819,
"eval_overall_precision": 0.9422110552763819,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.908,
"eval_steps_per_second": 10.181,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.3227895200252533,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.013,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9216867469879517,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05175183340907097,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.296,
"eval_samples_per_second": 574.317,
"eval_steps_per_second": 10.135,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.566750168800354,
"learning_rate": 2.25e-05,
"loss": 0.0145,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9240121580547112,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9382716049382716,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04927729815244675,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9460476787954831,
"eval_overall_precision": 0.9448621553884712,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.833,
"eval_steps_per_second": 10.197,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.2186298817396164,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.013,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.0439753420650959,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9323308270676693,
"eval_overall_precision": 0.93,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2939,
"eval_samples_per_second": 578.478,
"eval_steps_per_second": 10.208,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.40836167335510254,
"learning_rate": 2.15e-05,
"loss": 0.0126,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04749138653278351,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9363295880149813,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.3025,
"eval_samples_per_second": 561.944,
"eval_steps_per_second": 9.917,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.8158698678016663,
"learning_rate": 2.1e-05,
"loss": 0.0142,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04196289926767349,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9385194479297366,
"eval_overall_precision": 0.9373433583959899,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.908,
"eval_steps_per_second": 10.181,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.2486373484134674,
"learning_rate": 2.05e-05,
"loss": 0.0113,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9015544041450778,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9074626865671641,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9047619047619048,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06373338401317596,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9313358302122346,
"eval_overall_precision": 0.9255583126550868,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2946,
"eval_samples_per_second": 577.001,
"eval_steps_per_second": 10.182,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.5692731142044067,
"learning_rate": 2e-05,
"loss": 0.0121,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.052726853638887405,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9364881693648817,
"eval_overall_precision": 0.928395061728395,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2957,
"eval_samples_per_second": 574.821,
"eval_steps_per_second": 10.144,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.07468756288290024,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0115,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.8958333333333333,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8775510204081632,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.9313432835820896,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9285714285714286,
"eval_ORGANIZATION_recall": 0.9341317365269461,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.048753563314676285,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2946,
"eval_samples_per_second": 577.052,
"eval_steps_per_second": 10.183,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.09449464082717896,
"learning_rate": 1.9e-05,
"loss": 0.0112,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9244712990936556,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05517318844795227,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9414694894146949,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.627,
"eval_steps_per_second": 10.193,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.038850754499435425,
"learning_rate": 1.85e-05,
"loss": 0.0102,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.913946587537092,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9058823529411765,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04701891914010048,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2963,
"eval_samples_per_second": 573.823,
"eval_steps_per_second": 10.126,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.1799478977918625,
"learning_rate": 1.8e-05,
"loss": 0.0123,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05710792541503906,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9363295880149813,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2978,
"eval_samples_per_second": 570.773,
"eval_steps_per_second": 10.072,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.05153358355164528,
"learning_rate": 1.75e-05,
"loss": 0.0122,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9216867469879517,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.0565725676715374,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2959,
"eval_samples_per_second": 574.496,
"eval_steps_per_second": 10.138,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.2528524100780487,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0104,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.8823529411764706,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8181818181818182,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9130434782608696,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9483870967741935,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.0601673349738121,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9311639549436797,
"eval_overall_precision": 0.9276807980049875,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.3001,
"eval_samples_per_second": 566.49,
"eval_steps_per_second": 9.997,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.29999423027038574,
"learning_rate": 1.65e-05,
"loss": 0.0107,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05453917011618614,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9401496259351622,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2943,
"eval_samples_per_second": 577.556,
"eval_steps_per_second": 10.192,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.07306240499019623,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0103,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04836645722389221,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2942,
"eval_samples_per_second": 577.854,
"eval_steps_per_second": 10.197,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.2490108609199524,
"learning_rate": 1.55e-05,
"loss": 0.0113,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9123867069486405,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9207317073170732,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04641785845160484,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9349999999999999,
"eval_overall_precision": 0.9303482587064676,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.834,
"eval_steps_per_second": 10.179,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.8289707899093628,
"learning_rate": 1.5e-05,
"loss": 0.0101,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.900523560209424,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8865979381443299,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.9166666666666667,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.050225671380758286,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9375,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2933,
"eval_samples_per_second": 579.566,
"eval_steps_per_second": 10.228,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.3322184681892395,
"learning_rate": 1.45e-05,
"loss": 0.0095,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05536087974905968,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9351620947630923,
"eval_overall_precision": 0.9282178217821783,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2939,
"eval_samples_per_second": 578.421,
"eval_steps_per_second": 10.207,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.8135738968849182,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0098,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05878331884741783,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.294,
"eval_samples_per_second": 578.202,
"eval_steps_per_second": 10.204,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.3593475818634033,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0095,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05931860953569412,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2958,
"eval_samples_per_second": 574.669,
"eval_steps_per_second": 10.141,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.3202952742576599,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0093,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9305135951661632,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.054091017693281174,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9413233458177278,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.07,
"eval_steps_per_second": 10.201,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.08863040059804916,
"learning_rate": 1.25e-05,
"loss": 0.0083,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05632825568318367,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9401496259351622,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2977,
"eval_samples_per_second": 571.031,
"eval_steps_per_second": 10.077,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.5666746497154236,
"learning_rate": 1.2e-05,
"loss": 0.0093,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.8888888888888888,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8461538461538461,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9123867069486405,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9207317073170732,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.056217536330223083,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9326683291770573,
"eval_overall_precision": 0.9257425742574258,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2971,
"eval_samples_per_second": 572.138,
"eval_steps_per_second": 10.097,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.3464132249355316,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0094,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.929663608562691,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.95,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.054861877113580704,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9436795994993743,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2934,
"eval_samples_per_second": 579.434,
"eval_steps_per_second": 10.225,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.21085244417190552,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0082,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.8969072164948454,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.87,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9253731343283582,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9226190476190477,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.054944004863500595,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9401496259351622,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2957,
"eval_samples_per_second": 574.9,
"eval_steps_per_second": 10.145,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.4060479700565338,
"learning_rate": 1.05e-05,
"loss": 0.0084,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05838395282626152,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9348370927318297,
"eval_overall_precision": 0.9325,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.239,
"eval_steps_per_second": 10.187,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.48661842942237854,
"learning_rate": 1e-05,
"loss": 0.0087,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9361702127659574,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9506172839506173,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05529947951436043,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9436795994993743,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2955,
"eval_samples_per_second": 575.215,
"eval_steps_per_second": 10.151,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.24263687431812286,
"learning_rate": 9.5e-06,
"loss": 0.0084,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05996180325746536,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9341614906832298,
"eval_overall_precision": 0.9238329238329238,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.073,
"eval_steps_per_second": 10.201,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.1970207393169403,
"learning_rate": 9e-06,
"loss": 0.0075,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9015544041450778,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05396867170929909,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9363295880149813,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.297,
"eval_samples_per_second": 572.331,
"eval_steps_per_second": 10.1,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.44334614276885986,
"learning_rate": 8.500000000000002e-06,
"loss": 0.008,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05771942064166069,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2941,
"eval_samples_per_second": 578.11,
"eval_steps_per_second": 10.202,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.04559776559472084,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0077,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9221556886227545,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.061264559626579285,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9310344827586207,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2951,
"eval_samples_per_second": 576.01,
"eval_steps_per_second": 10.165,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.2589927315711975,
"learning_rate": 7.5e-06,
"loss": 0.0061,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05962163209915161,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.174,
"eval_steps_per_second": 10.15,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.6927934288978577,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0069,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9216867469879517,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05561165511608124,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9353233830845771,
"eval_overall_precision": 0.9261083743842364,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2948,
"eval_samples_per_second": 576.576,
"eval_steps_per_second": 10.175,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.7038125991821289,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0071,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9181286549707602,
"eval_ORGANIZATION_recall": 0.9401197604790419,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.057918768376111984,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2965,
"eval_samples_per_second": 573.301,
"eval_steps_per_second": 10.117,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.7621605396270752,
"learning_rate": 6e-06,
"loss": 0.008,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.8955223880597015,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8411214953271028,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.06091925501823425,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9328358208955224,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2929,
"eval_samples_per_second": 580.312,
"eval_steps_per_second": 10.241,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.36396142840385437,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0072,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05789695680141449,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9363295880149813,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2952,
"eval_samples_per_second": 575.858,
"eval_steps_per_second": 10.162,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.2463766634464264,
"learning_rate": 5e-06,
"loss": 0.0071,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9305135951661632,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05514437332749367,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.294,
"eval_samples_per_second": 578.321,
"eval_steps_per_second": 10.206,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.7866688966751099,
"learning_rate": 4.5e-06,
"loss": 0.0082,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.054316744208335876,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9451371571072318,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.295,
"eval_samples_per_second": 576.341,
"eval_steps_per_second": 10.171,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.19680312275886536,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0076,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.056269049644470215,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2961,
"eval_samples_per_second": 574.189,
"eval_steps_per_second": 10.133,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.5024588704109192,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0067,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9281437125748502,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05727045238018036,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9451371571072318,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2947,
"eval_samples_per_second": 576.815,
"eval_steps_per_second": 10.179,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.3682478070259094,
"learning_rate": 3e-06,
"loss": 0.0062,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05693649500608444,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2928,
"eval_samples_per_second": 580.59,
"eval_steps_per_second": 10.246,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.38271579146385193,
"learning_rate": 2.5e-06,
"loss": 0.0077,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05491955578327179,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9438202247191011,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2956,
"eval_samples_per_second": 575.141,
"eval_steps_per_second": 10.15,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.012570229358971119,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0072,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9221556886227545,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05807279795408249,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9401496259351622,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.298,
"eval_samples_per_second": 570.379,
"eval_steps_per_second": 10.066,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.1206221729516983,
"learning_rate": 1.5e-06,
"loss": 0.0067,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05665752664208412,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9389788293897883,
"eval_overall_precision": 0.9308641975308642,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2961,
"eval_samples_per_second": 574.182,
"eval_steps_per_second": 10.133,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.05178696662187576,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0071,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05722248554229736,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2945,
"eval_samples_per_second": 577.262,
"eval_steps_per_second": 10.187,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.08148621767759323,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0063,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.057887401431798935,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2944,
"eval_samples_per_second": 577.515,
"eval_steps_per_second": 10.191,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.7471449375152588,
"learning_rate": 0.0,
"loss": 0.0073,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05809829756617546,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2961,
"eval_samples_per_second": 574.074,
"eval_steps_per_second": 10.131,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4297274884593540.0,
"train_loss": 0.03787872251744072,
"train_runtime": 546.1852,
"train_samples_per_second": 280.125,
"train_steps_per_second": 17.576
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4297274884593540.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}