nerui-pt-pl5-0 / trainer_state.json
apwic's picture
End of training
07fa0a0 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": 0.8774209022521973,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.839,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.02040816326530612,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.25,
"eval_LOCATION_recall": 0.010638297872340425,
"eval_ORGANIZATION_f1": 0.33333333333333337,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.2766798418972332,
"eval_ORGANIZATION_recall": 0.41916167664670656,
"eval_PERSON_f1": 0.2997542997542998,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.22592592592592592,
"eval_PERSON_recall": 0.44525547445255476,
"eval_loss": 0.38439619541168213,
"eval_overall_accuracy": 0.8696132596685083,
"eval_overall_f1": 0.28540540540540543,
"eval_overall_precision": 0.2504743833017078,
"eval_overall_recall": 0.3316582914572864,
"eval_runtime": 0.2581,
"eval_samples_per_second": 658.659,
"eval_steps_per_second": 11.623,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.7088498473167419,
"learning_rate": 4.9e-05,
"loss": 0.3364,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.4878048780487805,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.5714285714285714,
"eval_LOCATION_recall": 0.425531914893617,
"eval_ORGANIZATION_f1": 0.6304909560723515,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.5545454545454546,
"eval_ORGANIZATION_recall": 0.7305389221556886,
"eval_PERSON_f1": 0.8951048951048951,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.8590604026845637,
"eval_PERSON_recall": 0.9343065693430657,
"eval_loss": 0.19179920852184296,
"eval_overall_accuracy": 0.9439226519337016,
"eval_overall_f1": 0.6929510155316608,
"eval_overall_precision": 0.6605922551252847,
"eval_overall_recall": 0.7286432160804021,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.681,
"eval_steps_per_second": 12.383,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.839773416519165,
"learning_rate": 4.85e-05,
"loss": 0.1872,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7351351351351353,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7472527472527473,
"eval_LOCATION_recall": 0.723404255319149,
"eval_ORGANIZATION_f1": 0.7909604519774012,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.7486631016042781,
"eval_ORGANIZATION_recall": 0.8383233532934131,
"eval_PERSON_f1": 0.9642857142857144,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9440559440559441,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.1045234203338623,
"eval_overall_accuracy": 0.9654696132596685,
"eval_overall_f1": 0.8376068376068376,
"eval_overall_precision": 0.8147268408551069,
"eval_overall_recall": 0.8618090452261307,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.982,
"eval_steps_per_second": 12.388,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.6193153262138367,
"learning_rate": 4.8e-05,
"loss": 0.1357,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8102564102564104,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7821782178217822,
"eval_LOCATION_recall": 0.8404255319148937,
"eval_ORGANIZATION_f1": 0.8034682080924855,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.776536312849162,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9819494584837546,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9714285714285714,
"eval_PERSON_recall": 0.9927007299270073,
"eval_loss": 0.07941848039627075,
"eval_overall_accuracy": 0.9715469613259669,
"eval_overall_f1": 0.8655256723716381,
"eval_overall_precision": 0.8428571428571429,
"eval_overall_recall": 0.8894472361809045,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.794,
"eval_steps_per_second": 12.385,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.6663116216659546,
"learning_rate": 4.75e-05,
"loss": 0.1109,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8542713567839195,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8095238095238095,
"eval_LOCATION_recall": 0.9042553191489362,
"eval_ORGANIZATION_f1": 0.8228228228228228,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8253012048192772,
"eval_ORGANIZATION_recall": 0.8203592814371258,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.061518434435129166,
"eval_overall_accuracy": 0.9784530386740331,
"eval_overall_f1": 0.8869565217391305,
"eval_overall_precision": 0.8771498771498771,
"eval_overall_recall": 0.8969849246231156,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.609,
"eval_steps_per_second": 12.364,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.8917957544326782,
"learning_rate": 4.7e-05,
"loss": 0.0945,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8349514563106796,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7678571428571429,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.838323353293413,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8383233532934131,
"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": 0.059839703142642975,
"eval_overall_accuracy": 0.9792817679558011,
"eval_overall_f1": 0.888068880688807,
"eval_overall_precision": 0.8698795180722891,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.546,
"eval_steps_per_second": 12.363,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.9868195652961731,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0834,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.8556701030927835,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.83,
"eval_LOCATION_recall": 0.8829787234042553,
"eval_ORGANIZATION_f1": 0.8664688427299703,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8588235294117647,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05131422355771065,
"eval_overall_accuracy": 0.9820441988950276,
"eval_overall_f1": 0.9029850746268657,
"eval_overall_precision": 0.8940886699507389,
"eval_overall_recall": 0.9120603015075377,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.576,
"eval_steps_per_second": 12.416,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.3709118068218231,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0779,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8380952380952381,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7586206896551724,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8616352201257861,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9072847682119205,
"eval_ORGANIZATION_recall": 0.8203592814371258,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05590811371803284,
"eval_overall_accuracy": 0.980110497237569,
"eval_overall_f1": 0.8977556109725686,
"eval_overall_precision": 0.8910891089108911,
"eval_overall_recall": 0.9045226130653267,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.342,
"eval_steps_per_second": 12.377,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 1.1680361032485962,
"learning_rate": 4.55e-05,
"loss": 0.0707,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.8476190476190476,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7672413793103449,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8473520249221184,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8831168831168831,
"eval_ORGANIZATION_recall": 0.8143712574850299,
"eval_PERSON_f1": 0.9818181818181817,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9782608695652174,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05033700540661812,
"eval_overall_accuracy": 0.9812154696132597,
"eval_overall_f1": 0.8933002481389579,
"eval_overall_precision": 0.8823529411764706,
"eval_overall_recall": 0.9045226130653267,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.676,
"eval_steps_per_second": 12.4,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.3654347360134125,
"learning_rate": 4.5e-05,
"loss": 0.0677,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.8712871287128713,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8148148148148148,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8727272727272728,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8834355828220859,
"eval_ORGANIZATION_recall": 0.8622754491017964,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.0475647859275341,
"eval_overall_accuracy": 0.9834254143646409,
"eval_overall_f1": 0.9118012422360248,
"eval_overall_precision": 0.9017199017199017,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.597,
"eval_steps_per_second": 12.346,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.6294370293617249,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0634,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.89,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.839622641509434,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8773006134969326,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.89937106918239,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04802582785487175,
"eval_overall_accuracy": 0.9842541436464088,
"eval_overall_f1": 0.9197994987468672,
"eval_overall_precision": 0.9175,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.621,
"eval_steps_per_second": 12.399,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 1.1109497547149658,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0569,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.8762886597938143,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.85,
"eval_LOCATION_recall": 0.9042553191489362,
"eval_ORGANIZATION_f1": 0.8716417910447762,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8690476190476191,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05169761925935745,
"eval_overall_accuracy": 0.9823204419889503,
"eval_overall_f1": 0.9138576779026217,
"eval_overall_precision": 0.9081885856079405,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.989,
"eval_steps_per_second": 12.353,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.9559684991836548,
"learning_rate": 4.35e-05,
"loss": 0.0583,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.9052631578947369,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.8731563421828908,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8604651162790697,
"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": 0.04232708364725113,
"eval_overall_accuracy": 0.9848066298342542,
"eval_overall_f1": 0.9201995012468827,
"eval_overall_precision": 0.9133663366336634,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.433,
"eval_steps_per_second": 12.396,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 1.1461082696914673,
"learning_rate": 4.3e-05,
"loss": 0.0538,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8828828828828829,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8855421686746988,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04221031069755554,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9276807980049875,
"eval_overall_precision": 0.9207920792079208,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.714,
"eval_steps_per_second": 12.401,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 1.1204590797424316,
"learning_rate": 4.25e-05,
"loss": 0.0497,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8716417910447762,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8690476190476191,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05186718702316284,
"eval_overall_accuracy": 0.9845303867403314,
"eval_overall_f1": 0.9190535491905356,
"eval_overall_precision": 0.9111111111111111,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2411,
"eval_samples_per_second": 705.12,
"eval_steps_per_second": 12.443,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.6826632618904114,
"learning_rate": 4.2e-05,
"loss": 0.0472,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9009900990099009,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8425925925925926,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.88,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9050632911392406,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04224754869937897,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9225,
"eval_overall_precision": 0.917910447761194,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.593,
"eval_steps_per_second": 12.399,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.8922760486602783,
"learning_rate": 4.15e-05,
"loss": 0.0437,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9154228855721392,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8598130841121495,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.8996960486322189,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9135802469135802,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04224979877471924,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9351620947630923,
"eval_overall_precision": 0.9282178217821783,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.247,
"eval_steps_per_second": 12.34,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.9579741358757019,
"learning_rate": 4.1e-05,
"loss": 0.0433,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9199999999999999,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8679245283018868,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.8714733542319749,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9144736842105263,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04857560992240906,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9242424242424242,
"eval_overall_precision": 0.9289340101522843,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.748,
"eval_steps_per_second": 12.384,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.3125724196434021,
"learning_rate": 4.05e-05,
"loss": 0.0397,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.8695652173913044,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7964601769911505,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8681672025723473,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.8083832335329342,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05412726849317551,
"eval_overall_accuracy": 0.9828729281767956,
"eval_overall_f1": 0.9090909090909092,
"eval_overall_precision": 0.9137055837563451,
"eval_overall_recall": 0.9045226130653267,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.519,
"eval_steps_per_second": 12.38,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 1.0277776718139648,
"learning_rate": 4e-05,
"loss": 0.0408,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9108910891089108,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8518518518518519,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.8875000000000001,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9281045751633987,
"eval_ORGANIZATION_recall": 0.8502994011976048,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04689141735434532,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9271356783919598,
"eval_overall_precision": 0.9271356783919598,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.221,
"eval_steps_per_second": 12.304,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.8402243256568909,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0388,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9381443298969071,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.91,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9009009009009009,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9036144578313253,
"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": 0.04327361658215523,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2415,
"eval_samples_per_second": 703.851,
"eval_steps_per_second": 12.421,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.4915686547756195,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0373,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9199999999999999,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8679245283018868,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.8948948948948949,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8975903614457831,
"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": 0.04407322406768799,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9330024813895781,
"eval_overall_precision": 0.9215686274509803,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2415,
"eval_samples_per_second": 703.813,
"eval_steps_per_second": 12.42,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.5029382109642029,
"learning_rate": 3.85e-05,
"loss": 0.0348,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.8823529411764706,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8181818181818182,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8785046728971964,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9155844155844156,
"eval_ORGANIZATION_recall": 0.844311377245509,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05189898982644081,
"eval_overall_accuracy": 0.9839779005524862,
"eval_overall_f1": 0.9172932330827068,
"eval_overall_precision": 0.915,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.571,
"eval_steps_per_second": 12.345,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 3.8196301460266113,
"learning_rate": 3.8e-05,
"loss": 0.0343,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9041916167664671,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"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": 0.043193645775318146,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9363295880149813,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2436,
"eval_samples_per_second": 697.845,
"eval_steps_per_second": 12.315,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.3661162853240967,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0371,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9145728643216081,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8666666666666667,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8787878787878789,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8895705521472392,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.0433676540851593,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9238451935081149,
"eval_overall_precision": 0.9181141439205955,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.273,
"eval_steps_per_second": 12.393,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.596856415271759,
"learning_rate": 3.7e-05,
"loss": 0.033,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9214659685863875,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9072164948453608,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.896969696969697,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9079754601226994,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.043336570262908936,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9331651954602774,
"eval_overall_precision": 0.9367088607594937,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.538,
"eval_steps_per_second": 12.38,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 1.5331320762634277,
"learning_rate": 3.65e-05,
"loss": 0.0315,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9148936170212766,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9148936170212766,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.8988095238095238,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.893491124260355,
"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": 0.04242286831140518,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9323308270676691,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2415,
"eval_samples_per_second": 703.851,
"eval_steps_per_second": 12.421,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 1.2568068504333496,
"learning_rate": 3.6e-05,
"loss": 0.0287,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8757763975155279,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9096774193548387,
"eval_ORGANIZATION_recall": 0.844311377245509,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04642978310585022,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9267676767676767,
"eval_overall_precision": 0.9314720812182741,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.188,
"eval_steps_per_second": 12.392,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.9163056015968323,
"learning_rate": 3.55e-05,
"loss": 0.0285,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.8823529411764706,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8181818181818182,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8690095846645367,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9315068493150684,
"eval_ORGANIZATION_recall": 0.8143712574850299,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05453680828213692,
"eval_overall_accuracy": 0.9848066298342542,
"eval_overall_f1": 0.915082382762991,
"eval_overall_precision": 0.9232736572890026,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.014,
"eval_steps_per_second": 12.406,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.9467638731002808,
"learning_rate": 3.5e-05,
"loss": 0.0287,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.8910891089108911,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.891566265060241,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.896969696969697,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9927007299270073,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9927007299270073,
"eval_PERSON_recall": 0.9927007299270073,
"eval_loss": 0.0493939183652401,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9257425742574257,
"eval_overall_precision": 0.9121951219512195,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.136,
"eval_steps_per_second": 12.408,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.16865617036819458,
"learning_rate": 3.45e-05,
"loss": 0.0276,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8957055214723927,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.041558887809515,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9370277078085643,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2414,
"eval_samples_per_second": 704.199,
"eval_steps_per_second": 12.427,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.9735445380210876,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.027,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9009900990099009,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8425925925925926,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8854489164086686,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04780115932226181,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9259723964868257,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.231,
"eval_steps_per_second": 12.392,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.5925016403198242,
"learning_rate": 3.35e-05,
"loss": 0.0269,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9018404907975461,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9245283018867925,
"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": 0.044178467243909836,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9382093316519546,
"eval_overall_precision": 0.9417721518987342,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.965,
"eval_steps_per_second": 12.352,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 1.0871243476867676,
"learning_rate": 3.3e-05,
"loss": 0.0231,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9012345679012346,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04651397094130516,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.964,
"eval_steps_per_second": 12.335,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.21386802196502686,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0249,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.8921568627450982,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8272727272727273,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.888888888888889,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9171974522292994,
"eval_ORGANIZATION_recall": 0.8622754491017964,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04889530688524246,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.925,
"eval_overall_precision": 0.9203980099502488,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.446,
"eval_steps_per_second": 12.378,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.18140262365341187,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0245,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"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": 0.04522449150681496,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9386733416770965,
"eval_overall_precision": 0.9351620947630923,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.541,
"eval_steps_per_second": 12.433,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.3071660101413727,
"learning_rate": 3.15e-05,
"loss": 0.0236,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.8955223880597015,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8411214953271028,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8902439024390244,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.906832298136646,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05357814207673073,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9263420724094882,
"eval_overall_precision": 0.9205955334987593,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2415,
"eval_samples_per_second": 704.031,
"eval_steps_per_second": 12.424,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.445687472820282,
"learning_rate": 3.1e-05,
"loss": 0.0225,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.8955223880597015,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8411214953271028,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8807339449541285,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.8622754491017964,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05375385284423828,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9225,
"eval_overall_precision": 0.917910447761194,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.652,
"eval_steps_per_second": 12.382,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 1.8128540515899658,
"learning_rate": 3.05e-05,
"loss": 0.0246,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9009009009009009,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9036144578313253,
"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": 0.05082034319639206,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.829,
"eval_steps_per_second": 12.385,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.41599786281585693,
"learning_rate": 3e-05,
"loss": 0.0233,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.8955223880597015,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8411214953271028,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9024390243902439,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.052833192050457,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9313358302122346,
"eval_overall_precision": 0.9255583126550868,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2412,
"eval_samples_per_second": 704.736,
"eval_steps_per_second": 12.437,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.6283953189849854,
"learning_rate": 2.95e-05,
"loss": 0.0222,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9041916167664671,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"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": 0.04490254819393158,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9348370927318297,
"eval_overall_precision": 0.9325,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.895,
"eval_steps_per_second": 12.386,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 1.0265886783599854,
"learning_rate": 2.9e-05,
"loss": 0.0208,
"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": 0.906906906906907,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9096385542168675,
"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": 0.04723484441637993,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9413233458177278,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.777,
"eval_steps_per_second": 12.367,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.4925542175769806,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0199,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.888888888888889,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.891566265060241,
"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": 0.05701683089137077,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9301745635910225,
"eval_overall_precision": 0.9232673267326733,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.977,
"eval_steps_per_second": 12.335,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.19192928075790405,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0206,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8490566037735849,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8660436137071652,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9025974025974026,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06194659322500229,
"eval_overall_accuracy": 0.9839779005524862,
"eval_overall_f1": 0.9118387909319899,
"eval_overall_precision": 0.9141414141414141,
"eval_overall_recall": 0.9095477386934674,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.791,
"eval_steps_per_second": 12.385,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.3135068416595459,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0219,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9319371727748691,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9175257731958762,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8869047619047618,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8816568047337278,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.0457727313041687,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9286608260325407,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.28,
"eval_steps_per_second": 12.376,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.42071783542633057,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0188,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8787878787878789,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8895705521472392,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.054580241441726685,
"eval_overall_accuracy": 0.9845303867403314,
"eval_overall_f1": 0.9281210592686002,
"eval_overall_precision": 0.9316455696202531,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.506,
"eval_steps_per_second": 12.415,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.6724656820297241,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0195,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.934010152284264,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8932038834951457,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04732288047671318,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9411764705882354,
"eval_overall_precision": 0.9376558603491272,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.658,
"eval_steps_per_second": 12.382,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.11307642608880997,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0174,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8773006134969326,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.89937106918239,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05758696049451828,
"eval_overall_accuracy": 0.9845303867403314,
"eval_overall_f1": 0.9234629861982434,
"eval_overall_precision": 0.9223057644110275,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.385,
"eval_steps_per_second": 12.413,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.12384165823459625,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0188,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.89,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.839622641509434,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8841463414634148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9006211180124224,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05333052948117256,
"eval_overall_accuracy": 0.9845303867403314,
"eval_overall_f1": 0.9211514392991239,
"eval_overall_precision": 0.9177057356608479,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.08,
"eval_steps_per_second": 12.39,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 1.0113431215286255,
"learning_rate": 2.5e-05,
"loss": 0.0201,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8902439024390244,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.906832298136646,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05218712240457535,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.924812030075188,
"eval_overall_precision": 0.9225,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.402,
"eval_steps_per_second": 12.431,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.026395199820399284,
"learning_rate": 2.45e-05,
"loss": 0.0184,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.8942598187311178,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9024390243902439,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05434548482298851,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.924812030075188,
"eval_overall_precision": 0.9225,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.835,
"eval_steps_per_second": 12.385,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.23059561848640442,
"learning_rate": 2.4e-05,
"loss": 0.0167,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8975903614457832,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9030303030303031,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9741697416974171,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9850746268656716,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.04944831132888794,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.903,
"eval_steps_per_second": 12.369,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.39829620718955994,
"learning_rate": 2.35e-05,
"loss": 0.0149,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8984615384615384,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.981549815498155,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925373134328358,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06188535690307617,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9255989911727616,
"eval_overall_precision": 0.9291139240506329,
"eval_overall_recall": 0.9221105527638191,
"eval_runtime": 0.2407,
"eval_samples_per_second": 706.219,
"eval_steps_per_second": 12.463,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.08308640122413635,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0175,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9263157894736843,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9014925373134329,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8988095238095238,
"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": 0.05221671983599663,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9323308270676691,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.101,
"eval_steps_per_second": 12.39,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.6507367491722107,
"learning_rate": 2.25e-05,
"loss": 0.0145,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9175257731958764,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9063444108761329,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9146341463414634,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.050912633538246155,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9385194479297366,
"eval_overall_precision": 0.9373433583959899,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.389,
"eval_steps_per_second": 12.307,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.2703074812889099,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0146,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"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": 0.05526857450604439,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9383647798742139,
"eval_overall_precision": 0.9395465994962217,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.77,
"eval_steps_per_second": 12.384,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.554535984992981,
"learning_rate": 2.15e-05,
"loss": 0.0155,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9054726368159204,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8504672897196262,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.882716049382716,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.910828025477707,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.061001092195510864,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.924812030075188,
"eval_overall_precision": 0.9225,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.241,
"eval_samples_per_second": 705.396,
"eval_steps_per_second": 12.448,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.062241412699222565,
"learning_rate": 2.1e-05,
"loss": 0.0145,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9263157894736843,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.888888888888889,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.891566265060241,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05654258653521538,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.778,
"eval_steps_per_second": 12.42,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.7023250460624695,
"learning_rate": 2.05e-05,
"loss": 0.0174,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.88,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8301886792452831,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.8640483383685801,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8719512195121951,
"eval_ORGANIZATION_recall": 0.8562874251497006,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05950825661420822,
"eval_overall_accuracy": 0.9834254143646409,
"eval_overall_f1": 0.9104477611940298,
"eval_overall_precision": 0.9014778325123153,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.073,
"eval_steps_per_second": 12.372,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 1.0031174421310425,
"learning_rate": 2e-05,
"loss": 0.0168,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8895705521472391,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9119496855345912,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.055906008929014206,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9273182957393483,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.886,
"eval_steps_per_second": 12.404,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.07340992987155914,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0172,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8869047619047618,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8816568047337278,
"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": 0.05632149800658226,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9313358302122346,
"eval_overall_precision": 0.9255583126550868,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.2,
"eval_steps_per_second": 12.374,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.0587456151843071,
"learning_rate": 1.9e-05,
"loss": 0.0142,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8895705521472391,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9119496855345912,
"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": 0.05989906191825867,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9273182957393483,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.293,
"eval_steps_per_second": 12.376,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.8025292754173279,
"learning_rate": 1.85e-05,
"loss": 0.013,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8828828828828829,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8855421686746988,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05182023346424103,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9288389513108615,
"eval_overall_precision": 0.9230769230769231,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.665,
"eval_steps_per_second": 12.365,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.06310325115919113,
"learning_rate": 1.8e-05,
"loss": 0.0137,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8792569659442724,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9102564102564102,
"eval_ORGANIZATION_recall": 0.8502994011976048,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.06394340097904205,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9207547169811321,
"eval_overall_precision": 0.9219143576826196,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.489,
"eval_steps_per_second": 12.397,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.08755341917276382,
"learning_rate": 1.75e-05,
"loss": 0.0125,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9012345679012346,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05584442988038063,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9343434343434344,
"eval_overall_precision": 0.9390862944162437,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2412,
"eval_samples_per_second": 704.694,
"eval_steps_per_second": 12.436,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.010304945521056652,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0129,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8895705521472391,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9119496855345912,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.05987972766160965,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9219143576826196,
"eval_overall_precision": 0.9242424242424242,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.465,
"eval_steps_per_second": 12.396,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.028544852510094643,
"learning_rate": 1.65e-05,
"loss": 0.0124,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.8910891089108911,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8695652173913042,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9032258064516129,
"eval_ORGANIZATION_recall": 0.8383233532934131,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06552106142044067,
"eval_overall_accuracy": 0.9839779005524862,
"eval_overall_f1": 0.9134253450439146,
"eval_overall_precision": 0.9122807017543859,
"eval_overall_recall": 0.914572864321608,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.396,
"eval_steps_per_second": 12.431,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.04386067017912865,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0146,
"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": 0.8868501529051986,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.90625,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.056066110730171204,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.38,
"eval_steps_per_second": 12.395,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.616553544998169,
"learning_rate": 1.55e-05,
"loss": 0.0125,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8835820895522388,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8809523809523809,
"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": 0.05580458790063858,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.924223602484472,
"eval_overall_precision": 0.914004914004914,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.099,
"eval_steps_per_second": 12.319,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 1.4747099876403809,
"learning_rate": 1.5e-05,
"loss": 0.0113,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8936170212765959,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"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": 0.05470040813088417,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.773,
"eval_steps_per_second": 12.331,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.5380275845527649,
"learning_rate": 1.45e-05,
"loss": 0.0121,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8957055214723927,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.0568201057612896,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9283018867924528,
"eval_overall_precision": 0.929471032745592,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.624,
"eval_steps_per_second": 12.364,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.687169075012207,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0116,
"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": 0.8875379939209727,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9012345679012346,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05489758774638176,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9261576971214018,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.69,
"eval_steps_per_second": 12.4,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.35669252276420593,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0139,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8936170212765959,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"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": 0.05638468265533447,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9261576971214018,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.534,
"eval_steps_per_second": 12.398,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.3573768138885498,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.012,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9079754601226994,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.053180016577243805,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9333333333333332,
"eval_overall_precision": 0.9345088161209067,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.201,
"eval_steps_per_second": 12.392,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.17985549569129944,
"learning_rate": 1.25e-05,
"loss": 0.0122,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8936170212765959,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"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": 0.0575711764395237,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.068,
"eval_steps_per_second": 12.407,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.6239557266235352,
"learning_rate": 1.2e-05,
"loss": 0.0112,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8875379939209727,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9012345679012346,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.06082821637392044,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9223057644110277,
"eval_overall_precision": 0.92,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2445,
"eval_samples_per_second": 695.176,
"eval_steps_per_second": 12.268,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.03245323896408081,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0108,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8847352024922118,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.922077922077922,
"eval_ORGANIZATION_recall": 0.8502994011976048,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06434763222932816,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9217171717171717,
"eval_overall_precision": 0.9263959390862944,
"eval_overall_recall": 0.9170854271356784,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.358,
"eval_steps_per_second": 12.342,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.23480919003486633,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0098,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8841463414634148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9006211180124224,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.0655590072274208,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9273182957393483,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.401,
"eval_steps_per_second": 12.413,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.02043691650032997,
"learning_rate": 1.05e-05,
"loss": 0.0107,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8942598187311178,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9024390243902439,
"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": 0.060443103313446045,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.515,
"eval_steps_per_second": 12.397,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.4943348169326782,
"learning_rate": 1e-05,
"loss": 0.0102,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"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": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05968930944800377,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9311639549436797,
"eval_overall_precision": 0.9276807980049875,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.722,
"eval_steps_per_second": 12.348,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.34316331148147583,
"learning_rate": 9.5e-06,
"loss": 0.0106,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8984615384615384,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.06144433468580246,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9283018867924528,
"eval_overall_precision": 0.929471032745592,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.669,
"eval_steps_per_second": 12.347,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.07222968339920044,
"learning_rate": 9e-06,
"loss": 0.011,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9278350515463918,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05597883090376854,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9370277078085643,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.698,
"eval_steps_per_second": 12.383,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.009474650956690311,
"learning_rate": 8.500000000000002e-06,
"loss": 0.01,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8957055214723927,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.060207221657037735,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9269521410579346,
"eval_overall_precision": 0.9292929292929293,
"eval_overall_recall": 0.9246231155778895,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.229,
"eval_steps_per_second": 12.392,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 1.08175790309906,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0098,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8902439024390244,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.906832298136646,
"eval_ORGANIZATION_recall": 0.874251497005988,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05689198151230812,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9284818067754077,
"eval_overall_precision": 0.9273182957393483,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.885,
"eval_steps_per_second": 12.369,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 1.0341581106185913,
"learning_rate": 7.5e-06,
"loss": 0.0105,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.888888888888889,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9171974522292994,
"eval_ORGANIZATION_recall": 0.8622754491017964,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05797797814011574,
"eval_overall_accuracy": 0.9853591160220995,
"eval_overall_f1": 0.9219143576826196,
"eval_overall_precision": 0.9242424242424242,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.2418,
"eval_samples_per_second": 702.959,
"eval_steps_per_second": 12.405,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.4196317195892334,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0108,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8990825688073394,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.91875,
"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": 0.057718031108379364,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.518,
"eval_steps_per_second": 12.433,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.22259293496608734,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0092,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8802395209580839,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8802395209580839,
"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": 0.05941590666770935,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9276807980049875,
"eval_overall_precision": 0.9207920792079208,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.503,
"eval_steps_per_second": 12.415,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.1983068883419037,
"learning_rate": 6e-06,
"loss": 0.01,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9145728643216081,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8666666666666667,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.8807339449541285,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.8622754491017964,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.058325644582509995,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9261576971214018,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.113,
"eval_steps_per_second": 12.355,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.7099875211715698,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0098,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8909090909090909,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.901840490797546,
"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": 0.05866383761167526,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9311639549436797,
"eval_overall_precision": 0.9276807980049875,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2412,
"eval_samples_per_second": 704.711,
"eval_steps_per_second": 12.436,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.04458107054233551,
"learning_rate": 5e-06,
"loss": 0.0093,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8963414634146342,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9130434782608695,
"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": 0.05550637096166611,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9323308270676691,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.923,
"eval_steps_per_second": 12.334,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.44196969270706177,
"learning_rate": 4.5e-06,
"loss": 0.0085,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8936170212765959,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"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": 0.055048685520887375,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.393,
"eval_steps_per_second": 12.307,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.22765903174877167,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0081,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8936170212765959,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"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": 0.05728204548358917,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.027,
"eval_steps_per_second": 12.371,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.1676163226366043,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0101,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8990825688073394,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.91875,
"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": 0.061041612178087234,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9358490566037736,
"eval_overall_precision": 0.9370277078085643,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.951,
"eval_steps_per_second": 12.37,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.07598228752613068,
"learning_rate": 3e-06,
"loss": 0.0095,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9285714285714286,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8921568627450981,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9046153846153847,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.930379746835443,
"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": 0.05960405617952347,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9395465994962218,
"eval_overall_precision": 0.9419191919191919,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.682,
"eval_steps_per_second": 12.365,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.7356542944908142,
"learning_rate": 2.5e-06,
"loss": 0.0092,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.896969696969697,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9079754601226994,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05594741553068161,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.348,
"eval_steps_per_second": 12.306,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.01336600724607706,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0089,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"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": 0.05663679912686348,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9286608260325407,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2445,
"eval_samples_per_second": 695.331,
"eval_steps_per_second": 12.271,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.6946114301681519,
"learning_rate": 1.5e-06,
"loss": 0.0085,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"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": 0.05698670819401741,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.186,
"eval_steps_per_second": 12.374,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.022725224494934082,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0084,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"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": 0.05713934078812599,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.14,
"eval_steps_per_second": 12.373,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.601417601108551,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0089,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8990825688073394,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.91875,
"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": 0.057130925357341766,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9333333333333332,
"eval_overall_precision": 0.9345088161209067,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.713,
"eval_steps_per_second": 12.348,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.11996118724346161,
"learning_rate": 0.0,
"loss": 0.0093,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8990825688073394,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.91875,
"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": 0.05734482780098915,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9333333333333332,
"eval_overall_precision": 0.9345088161209067,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.595,
"eval_steps_per_second": 12.399,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4297274884593540.0,
"train_loss": 0.03881123491252462,
"train_runtime": 486.5603,
"train_samples_per_second": 314.452,
"train_steps_per_second": 19.73
}
],
"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
}