nerui-pt-pl10-0 / trainer_state.json
apwic's picture
End of training
cd322e8 verified
raw
history blame
111 kB
{
"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": 0.9210596680641174,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8344,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.058823529411764705,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.375,
"eval_LOCATION_recall": 0.031914893617021274,
"eval_ORGANIZATION_f1": 0.24365482233502536,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.21145374449339208,
"eval_ORGANIZATION_recall": 0.2874251497005988,
"eval_PERSON_f1": 0.3231707317073171,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.2774869109947644,
"eval_PERSON_recall": 0.38686131386861317,
"eval_loss": 0.3986935019493103,
"eval_overall_accuracy": 0.8662983425414365,
"eval_overall_f1": 0.25242718446601947,
"eval_overall_precision": 0.24413145539906103,
"eval_overall_recall": 0.2613065326633166,
"eval_runtime": 0.6096,
"eval_samples_per_second": 278.888,
"eval_steps_per_second": 4.922,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.7666553854942322,
"learning_rate": 4.9e-05,
"loss": 0.359,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.4020618556701031,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.39,
"eval_LOCATION_recall": 0.4148936170212766,
"eval_ORGANIZATION_f1": 0.6078431372549018,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.5145228215767634,
"eval_ORGANIZATION_recall": 0.7425149700598802,
"eval_PERSON_f1": 0.8733333333333334,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.803680981595092,
"eval_PERSON_recall": 0.9562043795620438,
"eval_loss": 0.23019741475582123,
"eval_overall_accuracy": 0.937292817679558,
"eval_overall_f1": 0.6518847006651886,
"eval_overall_precision": 0.5833333333333334,
"eval_overall_recall": 0.7386934673366834,
"eval_runtime": 0.6379,
"eval_samples_per_second": 266.502,
"eval_steps_per_second": 4.703,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.988224983215332,
"learning_rate": 4.85e-05,
"loss": 0.1857,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.761904761904762,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7578947368421053,
"eval_LOCATION_recall": 0.7659574468085106,
"eval_ORGANIZATION_f1": 0.7506849315068495,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.6919191919191919,
"eval_ORGANIZATION_recall": 0.8203592814371258,
"eval_PERSON_f1": 0.971223021582734,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9574468085106383,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.10827086865901947,
"eval_overall_accuracy": 0.96353591160221,
"eval_overall_f1": 0.826923076923077,
"eval_overall_precision": 0.7926267281105991,
"eval_overall_recall": 0.864321608040201,
"eval_runtime": 0.6435,
"eval_samples_per_second": 264.161,
"eval_steps_per_second": 4.662,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 0.8629367351531982,
"learning_rate": 4.8e-05,
"loss": 0.1288,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.852791878172589,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8155339805825242,
"eval_LOCATION_recall": 0.8936170212765957,
"eval_ORGANIZATION_f1": 0.817391304347826,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.7921348314606742,
"eval_ORGANIZATION_recall": 0.844311377245509,
"eval_PERSON_f1": 0.9708029197080292,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9708029197080292,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.07415713369846344,
"eval_overall_accuracy": 0.9740331491712707,
"eval_overall_f1": 0.877450980392157,
"eval_overall_precision": 0.8564593301435407,
"eval_overall_recall": 0.8994974874371859,
"eval_runtime": 0.659,
"eval_samples_per_second": 257.95,
"eval_steps_per_second": 4.552,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.7485966086387634,
"learning_rate": 4.75e-05,
"loss": 0.108,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8350515463917526,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.81,
"eval_LOCATION_recall": 0.8617021276595744,
"eval_ORGANIZATION_f1": 0.8656716417910446,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8630952380952381,
"eval_ORGANIZATION_recall": 0.8682634730538922,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.06545506417751312,
"eval_overall_accuracy": 0.9765193370165746,
"eval_overall_f1": 0.8991282689912827,
"eval_overall_precision": 0.891358024691358,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.6364,
"eval_samples_per_second": 267.117,
"eval_steps_per_second": 4.714,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 0.6281290054321289,
"learning_rate": 4.7e-05,
"loss": 0.0921,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8700000000000001,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8207547169811321,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.8571428571428571,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8520710059171598,
"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": 0.05315474793314934,
"eval_overall_accuracy": 0.9812154696132597,
"eval_overall_f1": 0.9048207663782446,
"eval_overall_precision": 0.8905109489051095,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.6801,
"eval_samples_per_second": 249.974,
"eval_steps_per_second": 4.411,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.7421153783798218,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0824,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.854368932038835,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7857142857142857,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.84472049689441,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8774193548387097,
"eval_ORGANIZATION_recall": 0.8143712574850299,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05913132056593895,
"eval_overall_accuracy": 0.9770718232044199,
"eval_overall_f1": 0.8963795255930087,
"eval_overall_precision": 0.890818858560794,
"eval_overall_recall": 0.9020100502512562,
"eval_runtime": 0.6246,
"eval_samples_per_second": 272.184,
"eval_steps_per_second": 4.803,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.46505409479141235,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0751,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8530805687203793,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.7692307692307693,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.851963746223565,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8597560975609756,
"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": 0.053421638906002045,
"eval_overall_accuracy": 0.9803867403314918,
"eval_overall_f1": 0.8981595092024539,
"eval_overall_precision": 0.8776978417266187,
"eval_overall_recall": 0.9195979899497487,
"eval_runtime": 0.6269,
"eval_samples_per_second": 271.197,
"eval_steps_per_second": 4.786,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.2823048532009125,
"learning_rate": 4.55e-05,
"loss": 0.0697,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.8865979381443299,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.86,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.9,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.884393063583815,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04149297997355461,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9280397022332505,
"eval_overall_precision": 0.9166666666666666,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6324,
"eval_samples_per_second": 268.807,
"eval_steps_per_second": 4.744,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 1.3036563396453857,
"learning_rate": 4.5e-05,
"loss": 0.0657,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9052631578947369,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.898550724637681,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8707865168539326,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04033806174993515,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9318463444857498,
"eval_overall_precision": 0.9193154034229829,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6382,
"eval_samples_per_second": 266.364,
"eval_steps_per_second": 4.701,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.6182276606559753,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0639,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8948948948948949,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8975903614457831,
"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": 0.04298192635178566,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9325,
"eval_overall_precision": 0.927860696517413,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6297,
"eval_samples_per_second": 269.989,
"eval_steps_per_second": 4.765,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.816596269607544,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0571,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.896551724137931,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8348623853211009,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9079754601226994,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"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": 0.054365966469049454,
"eval_overall_accuracy": 0.9839779005524862,
"eval_overall_f1": 0.9338327091136079,
"eval_overall_precision": 0.9280397022332506,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6386,
"eval_samples_per_second": 266.219,
"eval_steps_per_second": 4.698,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.7130789160728455,
"learning_rate": 4.35e-05,
"loss": 0.0546,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8955223880597015,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8928571428571429,
"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": 0.0452798567712307,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9291925465838509,
"eval_overall_precision": 0.918918918918919,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6239,
"eval_samples_per_second": 272.474,
"eval_steps_per_second": 4.808,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.5757063031196594,
"learning_rate": 4.3e-05,
"loss": 0.0494,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9319371727748691,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9175257731958762,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9017341040462428,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8715083798882681,
"eval_ORGANIZATION_recall": 0.9341317365269461,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.039157819002866745,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9369592088998764,
"eval_overall_precision": 0.9221411192214112,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6371,
"eval_samples_per_second": 266.828,
"eval_steps_per_second": 4.709,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.44823992252349854,
"learning_rate": 4.25e-05,
"loss": 0.0491,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9015544041450778,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.8988095238095238,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.893491124260355,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.03682849183678627,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9288389513108615,
"eval_overall_precision": 0.9230769230769231,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6294,
"eval_samples_per_second": 270.104,
"eval_steps_per_second": 4.767,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.6802188754081726,
"learning_rate": 4.2e-05,
"loss": 0.0486,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9854014598540146,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9854014598540146,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.039052676409482956,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6307,
"eval_samples_per_second": 269.553,
"eval_steps_per_second": 4.757,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 1.9554082155227661,
"learning_rate": 4.15e-05,
"loss": 0.0467,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.913946587537092,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9058823529411765,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.03962372615933418,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9368029739776953,
"eval_overall_precision": 0.9242053789731052,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6833,
"eval_samples_per_second": 248.797,
"eval_steps_per_second": 4.391,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.4921131432056427,
"learning_rate": 4.1e-05,
"loss": 0.0401,
"step": 1728
},
{
"epoch": 18.0,
"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": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04431615769863129,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9371859296482412,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6314,
"eval_samples_per_second": 269.245,
"eval_steps_per_second": 4.751,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.25470882654190063,
"learning_rate": 4.05e-05,
"loss": 0.0414,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.8975609756097561,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8288288288288288,
"eval_LOCATION_recall": 0.9787234042553191,
"eval_ORGANIZATION_f1": 0.9074074074074076,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9363057324840764,
"eval_ORGANIZATION_recall": 0.8802395209580839,
"eval_PERSON_f1": 0.9781021897810219,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9781021897810219,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.047639016062021255,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9290161892901618,
"eval_overall_precision": 0.9209876543209876,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6302,
"eval_samples_per_second": 269.758,
"eval_steps_per_second": 4.76,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.4328829050064087,
"learning_rate": 4e-05,
"loss": 0.0404,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.8955223880597015,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8411214953271028,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.045904871076345444,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9379652605459057,
"eval_overall_precision": 0.9264705882352942,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6278,
"eval_samples_per_second": 270.771,
"eval_steps_per_second": 4.778,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.7747119665145874,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0411,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9191919191919191,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.875,
"eval_LOCATION_recall": 0.9680851063829787,
"eval_ORGANIZATION_f1": 0.9337349397590362,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04292783886194229,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.6383,
"eval_samples_per_second": 266.316,
"eval_steps_per_second": 4.7,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.09759626537561417,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0354,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8941176470588235,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8786127167630058,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04124228283762932,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9353233830845771,
"eval_overall_precision": 0.9261083743842364,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6306,
"eval_samples_per_second": 269.576,
"eval_steps_per_second": 4.757,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.38919568061828613,
"learning_rate": 3.85e-05,
"loss": 0.0343,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.8660436137071652,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9025974025974026,
"eval_ORGANIZATION_recall": 0.8323353293413174,
"eval_PERSON_f1": 0.9710144927536232,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9640287769784173,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.057296257466077805,
"eval_overall_accuracy": 0.9803867403314918,
"eval_overall_f1": 0.9095477386934674,
"eval_overall_precision": 0.9095477386934674,
"eval_overall_recall": 0.9095477386934674,
"eval_runtime": 0.6419,
"eval_samples_per_second": 264.844,
"eval_steps_per_second": 4.674,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.42174291610717773,
"learning_rate": 3.8e-05,
"loss": 0.0337,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9134328358208956,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9107142857142857,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04203649237751961,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6242,
"eval_samples_per_second": 272.332,
"eval_steps_per_second": 4.806,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.23052428662776947,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0321,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9183673469387754,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9166666666666667,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.047372255474328995,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9427860696517413,
"eval_overall_precision": 0.9334975369458128,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6301,
"eval_samples_per_second": 269.795,
"eval_steps_per_second": 4.761,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.7009490728378296,
"learning_rate": 3.7e-05,
"loss": 0.0334,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9080118694362018,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04177287593483925,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9398496240601504,
"eval_overall_precision": 0.9375,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6297,
"eval_samples_per_second": 269.966,
"eval_steps_per_second": 4.764,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.4570506513118744,
"learning_rate": 3.65e-05,
"loss": 0.0319,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9309309309309309,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9337349397590361,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.040432997047901154,
"eval_overall_accuracy": 0.9897790055248619,
"eval_overall_f1": 0.9508196721311476,
"eval_overall_precision": 0.9544303797468354,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6187,
"eval_samples_per_second": 274.773,
"eval_steps_per_second": 4.849,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.4050446152687073,
"learning_rate": 3.6e-05,
"loss": 0.0342,
"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": 0.929663608562691,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.95,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.039812587201595306,
"eval_overall_accuracy": 0.9895027624309393,
"eval_overall_f1": 0.9472361809045227,
"eval_overall_precision": 0.9472361809045227,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6967,
"eval_samples_per_second": 243.998,
"eval_steps_per_second": 4.306,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 1.4977127313613892,
"learning_rate": 3.55e-05,
"loss": 0.0322,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.8787878787878788,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8365384615384616,
"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": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04951874166727066,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9238451935081149,
"eval_overall_precision": 0.9181141439205955,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6319,
"eval_samples_per_second": 269.012,
"eval_steps_per_second": 4.747,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 1.1560513973236084,
"learning_rate": 3.5e-05,
"loss": 0.0285,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9107142857142857,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9053254437869822,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04342739284038544,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6265,
"eval_samples_per_second": 271.349,
"eval_steps_per_second": 4.789,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.13555112481117249,
"learning_rate": 3.45e-05,
"loss": 0.0281,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9134328358208956,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9107142857142857,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.03950895369052887,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6269,
"eval_samples_per_second": 271.167,
"eval_steps_per_second": 4.785,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 1.0813785791397095,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0261,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9045226130653266,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8571428571428571,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04411884769797325,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9351620947630923,
"eval_overall_precision": 0.9282178217821783,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6286,
"eval_samples_per_second": 270.421,
"eval_steps_per_second": 4.772,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.798093318939209,
"learning_rate": 3.35e-05,
"loss": 0.0267,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04117562994360924,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9370277078085643,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6266,
"eval_samples_per_second": 271.309,
"eval_steps_per_second": 4.788,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.09470222890377045,
"learning_rate": 3.3e-05,
"loss": 0.0254,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.8790560471976401,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8662790697674418,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.047401439398527145,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.925,
"eval_overall_precision": 0.9203980099502488,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6434,
"eval_samples_per_second": 264.206,
"eval_steps_per_second": 4.662,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.868523895740509,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0234,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9222797927461138,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9096385542168675,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.0433831587433815,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9348370927318297,
"eval_overall_precision": 0.9325,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6299,
"eval_samples_per_second": 269.882,
"eval_steps_per_second": 4.763,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.6940657496452332,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0248,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9119170984455959,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9075144508670521,
"eval_ORGANIZATION_recall": 0.9401197604790419,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04494161158800125,
"eval_overall_accuracy": 0.9892265193370166,
"eval_overall_f1": 0.9427860696517413,
"eval_overall_precision": 0.9334975369458128,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.6217,
"eval_samples_per_second": 273.459,
"eval_steps_per_second": 4.826,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 1.5529848337173462,
"learning_rate": 3.15e-05,
"loss": 0.0227,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9119170984455959,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.045806463807821274,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.63,
"eval_samples_per_second": 269.824,
"eval_steps_per_second": 4.762,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.3154653012752533,
"learning_rate": 3.1e-05,
"loss": 0.0232,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"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": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04870746657252312,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.93,
"eval_overall_precision": 0.9253731343283582,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6348,
"eval_samples_per_second": 267.802,
"eval_steps_per_second": 4.726,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.2102024406194687,
"learning_rate": 3.05e-05,
"loss": 0.0217,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.049260273575782776,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9361702127659574,
"eval_overall_precision": 0.9326683291770573,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6896,
"eval_samples_per_second": 246.534,
"eval_steps_per_second": 4.351,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.4227250814437866,
"learning_rate": 3e-05,
"loss": 0.0228,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9779411764705882,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9851851851851852,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04727453738451004,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6242,
"eval_samples_per_second": 272.368,
"eval_steps_per_second": 4.806,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.07798568159341812,
"learning_rate": 2.95e-05,
"loss": 0.0216,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04285992309451103,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9375,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6244,
"eval_samples_per_second": 272.245,
"eval_steps_per_second": 4.804,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.4483208656311035,
"learning_rate": 2.9e-05,
"loss": 0.0195,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9074074074074076,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9363057324840764,
"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": 0.04589952528476715,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9370277078085643,
"eval_overall_precision": 0.9393939393939394,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6308,
"eval_samples_per_second": 269.497,
"eval_steps_per_second": 4.756,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.8039036393165588,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0217,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.892966360856269,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9125,
"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": 0.04960371553897858,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9306431273644388,
"eval_overall_precision": 0.9341772151898734,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6418,
"eval_samples_per_second": 264.862,
"eval_steps_per_second": 4.674,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.26074641942977905,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0182,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9113149847094801,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.93125,
"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": 0.051832567900419235,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9385194479297366,
"eval_overall_precision": 0.9373433583959899,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6318,
"eval_samples_per_second": 269.092,
"eval_steps_per_second": 4.749,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.33334818482398987,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0202,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9157894736842105,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.925531914893617,
"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": 0.04459786042571068,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9380530973451328,
"eval_overall_precision": 0.9440203562340967,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6329,
"eval_samples_per_second": 268.601,
"eval_steps_per_second": 4.74,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.8288144469261169,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0192,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"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": 0.04660237953066826,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9336670838548186,
"eval_overall_precision": 0.9301745635910225,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.624,
"eval_samples_per_second": 272.419,
"eval_steps_per_second": 4.807,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.2075764685869217,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0185,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9325153374233128,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9705882352941176,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9777777777777777,
"eval_PERSON_recall": 0.9635036496350365,
"eval_loss": 0.045554447919130325,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6336,
"eval_samples_per_second": 268.308,
"eval_steps_per_second": 4.735,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.25534167885780334,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0191,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04581255465745926,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9371859296482412,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.629,
"eval_samples_per_second": 270.273,
"eval_steps_per_second": 4.77,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.3191823363304138,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0177,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.0495520643889904,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9410288582183186,
"eval_overall_precision": 0.9398496240601504,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6366,
"eval_samples_per_second": 267.031,
"eval_steps_per_second": 4.712,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.781195878982544,
"learning_rate": 2.5e-05,
"loss": 0.0176,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.898989898989899,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8557692307692307,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9166666666666667,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04734129086136818,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9379652605459057,
"eval_overall_precision": 0.9264705882352942,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.6357,
"eval_samples_per_second": 267.412,
"eval_steps_per_second": 4.719,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.04111425578594208,
"learning_rate": 2.45e-05,
"loss": 0.0167,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9137055837563451,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8737864077669902,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.8922155688622756,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.8922155688622755,
"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": 0.046640992164611816,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9315068493150684,
"eval_overall_precision": 0.9234567901234568,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6346,
"eval_samples_per_second": 267.893,
"eval_steps_per_second": 4.728,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.2644822895526886,
"learning_rate": 2.4e-05,
"loss": 0.0162,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.04314136505126953,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9319899244332494,
"eval_overall_precision": 0.9343434343434344,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6294,
"eval_samples_per_second": 270.078,
"eval_steps_per_second": 4.766,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.06157953664660454,
"learning_rate": 2.35e-05,
"loss": 0.0154,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.8888888888888888,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8461538461538461,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9101796407185628,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04938226565718651,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9328358208955224,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6341,
"eval_samples_per_second": 268.093,
"eval_steps_per_second": 4.731,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 1.6651655435562134,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0161,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9101796407185628,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04377256706357002,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9349999999999999,
"eval_overall_precision": 0.9303482587064676,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6259,
"eval_samples_per_second": 271.593,
"eval_steps_per_second": 4.793,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.6327649354934692,
"learning_rate": 2.25e-05,
"loss": 0.014,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"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": 0.04936566576361656,
"eval_overall_accuracy": 0.9878453038674033,
"eval_overall_f1": 0.9382093316519546,
"eval_overall_precision": 0.9417721518987342,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6296,
"eval_samples_per_second": 270.031,
"eval_steps_per_second": 4.765,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.6683529615402222,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0149,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9207317073170732,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.0460093729197979,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9420654911838791,
"eval_overall_precision": 0.9444444444444444,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.618,
"eval_samples_per_second": 275.059,
"eval_steps_per_second": 4.854,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.047909464687108994,
"learning_rate": 2.15e-05,
"loss": 0.0126,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8910891089108911,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04427206888794899,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6301,
"eval_samples_per_second": 269.779,
"eval_steps_per_second": 4.761,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.12404149770736694,
"learning_rate": 2.1e-05,
"loss": 0.0148,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9166666666666666,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9216867469879517,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04789452254772186,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9433962264150944,
"eval_overall_precision": 0.9445843828715366,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6227,
"eval_samples_per_second": 273.006,
"eval_steps_per_second": 4.818,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.7699698209762573,
"learning_rate": 2.05e-05,
"loss": 0.0136,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9035532994923857,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9101796407185628,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.050934724509716034,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9351620947630923,
"eval_overall_precision": 0.9282178217821783,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6327,
"eval_samples_per_second": 268.696,
"eval_steps_per_second": 4.742,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.41864609718322754,
"learning_rate": 2e-05,
"loss": 0.0141,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9244712990936556,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05812539532780647,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6207,
"eval_samples_per_second": 273.869,
"eval_steps_per_second": 4.833,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.12164263427257538,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0135,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04735632613301277,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.6266,
"eval_samples_per_second": 271.286,
"eval_steps_per_second": 4.787,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.6149705052375793,
"learning_rate": 1.9e-05,
"loss": 0.0135,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9816849816849818,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9852941176470589,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.052522845566272736,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9360100376411543,
"eval_overall_precision": 0.9348370927318296,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6286,
"eval_samples_per_second": 270.449,
"eval_steps_per_second": 4.773,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.4814046323299408,
"learning_rate": 1.85e-05,
"loss": 0.0125,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.05100388079881668,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9308176100628931,
"eval_overall_precision": 0.9319899244332494,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6453,
"eval_samples_per_second": 263.442,
"eval_steps_per_second": 4.649,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.022650260478258133,
"learning_rate": 1.8e-05,
"loss": 0.0142,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9128205128205128,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8811881188118812,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.905775075987842,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.053282029926776886,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6352,
"eval_samples_per_second": 267.632,
"eval_steps_per_second": 4.723,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.6195140480995178,
"learning_rate": 1.75e-05,
"loss": 0.0137,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.8775510204081632,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8431372549019608,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.905775075987842,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05343993753194809,
"eval_overall_accuracy": 0.9856353591160221,
"eval_overall_f1": 0.9259723964868257,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6318,
"eval_samples_per_second": 269.088,
"eval_steps_per_second": 4.749,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.10300092399120331,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0132,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.8969072164948454,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.87,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9192546583850931,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9548387096774194,
"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": 0.052333325147628784,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9353612167300379,
"eval_overall_precision": 0.9437340153452686,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6169,
"eval_samples_per_second": 275.55,
"eval_steps_per_second": 4.863,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.05577034875750542,
"learning_rate": 1.65e-05,
"loss": 0.0136,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"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": 0.054235268384218216,
"eval_overall_accuracy": 0.9850828729281768,
"eval_overall_f1": 0.9236545682102627,
"eval_overall_precision": 0.9201995012468828,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6279,
"eval_samples_per_second": 270.75,
"eval_steps_per_second": 4.778,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.5485521554946899,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0113,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.8958333333333333,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8775510204081632,
"eval_LOCATION_recall": 0.9148936170212766,
"eval_ORGANIZATION_f1": 0.9041916167664671,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04972825199365616,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9275,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6154,
"eval_samples_per_second": 276.24,
"eval_steps_per_second": 4.875,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 2.3350493907928467,
"learning_rate": 1.55e-05,
"loss": 0.0121,
"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": 0.9107692307692307,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"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": 0.04727216437458992,
"eval_overall_accuracy": 0.9883977900552486,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6316,
"eval_samples_per_second": 269.17,
"eval_steps_per_second": 4.75,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.022277483716607094,
"learning_rate": 1.5e-05,
"loss": 0.0124,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9015544041450778,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"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": 0.0438135601580143,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9395465994962218,
"eval_overall_precision": 0.9419191919191919,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.6316,
"eval_samples_per_second": 269.17,
"eval_steps_per_second": 4.75,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.6009500026702881,
"learning_rate": 1.45e-05,
"loss": 0.0132,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.8969072164948454,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.87,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9161676646706587,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.04383927583694458,
"eval_overall_accuracy": 0.9881215469613259,
"eval_overall_f1": 0.9349999999999999,
"eval_overall_precision": 0.9303482587064676,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6237,
"eval_samples_per_second": 272.546,
"eval_steps_per_second": 4.81,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.5048597455024719,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0127,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9221556886227545,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05126424506306648,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.625,
"eval_samples_per_second": 271.996,
"eval_steps_per_second": 4.8,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.09407883137464523,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0107,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.8944723618090452,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8476190476190476,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9079754601226994,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"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": 0.049858223646879196,
"eval_overall_accuracy": 0.9875690607734806,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6365,
"eval_samples_per_second": 267.101,
"eval_steps_per_second": 4.714,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.14418302476406097,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0114,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9119170984455959,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.9743589743589743,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9779411764705882,
"eval_PERSON_recall": 0.9708029197080292,
"eval_loss": 0.046700652688741684,
"eval_overall_accuracy": 0.988950276243094,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6286,
"eval_samples_per_second": 270.46,
"eval_steps_per_second": 4.773,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.5593026876449585,
"learning_rate": 1.25e-05,
"loss": 0.0103,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04857783764600754,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9386733416770965,
"eval_overall_precision": 0.9351620947630923,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.6315,
"eval_samples_per_second": 269.192,
"eval_steps_per_second": 4.75,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.585735023021698,
"learning_rate": 1.2e-05,
"loss": 0.0101,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9051987767584098,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.8862275449101796,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.051167141646146774,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6285,
"eval_samples_per_second": 270.502,
"eval_steps_per_second": 4.774,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.31444257497787476,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0101,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.8963414634146342,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9130434782608695,
"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": 0.05296648293733597,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9259723964868257,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6301,
"eval_samples_per_second": 269.786,
"eval_steps_per_second": 4.761,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.1825409233570099,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0094,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9156626506024097,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.04947284236550331,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9396984924623115,
"eval_overall_precision": 0.9396984924623115,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.634,
"eval_samples_per_second": 268.141,
"eval_steps_per_second": 4.732,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.1238226667046547,
"learning_rate": 1.05e-05,
"loss": 0.0099,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9281437125748502,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9281437125748503,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05076669156551361,
"eval_overall_accuracy": 0.9886740331491712,
"eval_overall_f1": 0.9484276729559749,
"eval_overall_precision": 0.9496221662468514,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.6272,
"eval_samples_per_second": 271.04,
"eval_steps_per_second": 4.783,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.8318716883659363,
"learning_rate": 1e-05,
"loss": 0.0097,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.8923076923076922,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8613861386138614,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9926470588235294,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05529572069644928,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6324,
"eval_samples_per_second": 268.804,
"eval_steps_per_second": 4.744,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.2662683427333832,
"learning_rate": 9.5e-06,
"loss": 0.009,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"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": 0.055139243602752686,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9311639549436797,
"eval_overall_precision": 0.9276807980049875,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6317,
"eval_samples_per_second": 269.113,
"eval_steps_per_second": 4.749,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.9171668291091919,
"learning_rate": 9e-06,
"loss": 0.0096,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9129129129129129,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.989010989010989,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9926470588235294,
"eval_PERSON_recall": 0.9854014598540146,
"eval_loss": 0.05441170930862427,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6317,
"eval_samples_per_second": 269.122,
"eval_steps_per_second": 4.749,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 1.0301741361618042,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0103,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9101796407185628,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05301690846681595,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6273,
"eval_samples_per_second": 271.008,
"eval_steps_per_second": 4.783,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.017641935497522354,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0094,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9118541033434651,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.054743442684412,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9323308270676691,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6197,
"eval_samples_per_second": 274.342,
"eval_steps_per_second": 4.841,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.07819229364395142,
"learning_rate": 7.5e-06,
"loss": 0.0087,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.053189270198345184,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9346733668341709,
"eval_overall_precision": 0.9346733668341709,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6217,
"eval_samples_per_second": 273.439,
"eval_steps_per_second": 4.825,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 1.6688259840011597,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0094,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05546409264206886,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9321608040201005,
"eval_overall_precision": 0.9321608040201005,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6298,
"eval_samples_per_second": 269.948,
"eval_steps_per_second": 4.764,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.021393638104200363,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0092,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.8910891089108911,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9574468085106383,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.054414279758930206,
"eval_overall_accuracy": 0.9870165745856354,
"eval_overall_f1": 0.9326683291770573,
"eval_overall_precision": 0.9257425742574258,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6377,
"eval_samples_per_second": 266.571,
"eval_steps_per_second": 4.704,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.2767832577228546,
"learning_rate": 6e-06,
"loss": 0.0098,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9079754601226994,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"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": 0.05563962459564209,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.929471032745592,
"eval_overall_precision": 0.9318181818181818,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6337,
"eval_samples_per_second": 268.276,
"eval_steps_per_second": 4.734,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.8828210830688477,
"learning_rate": 5.500000000000001e-06,
"loss": 0.008,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.055685095489025116,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9309912170639899,
"eval_overall_precision": 0.9298245614035088,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.7049,
"eval_samples_per_second": 241.179,
"eval_steps_per_second": 4.256,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.1280243843793869,
"learning_rate": 5e-06,
"loss": 0.0087,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9146341463414633,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.053050216287374496,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.9335006273525721,
"eval_overall_precision": 0.9323308270676691,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6389,
"eval_samples_per_second": 266.077,
"eval_steps_per_second": 4.695,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.41627761721611023,
"learning_rate": 4.5e-06,
"loss": 0.0094,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9024390243902439,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"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": 0.05441103130578995,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9259723964868257,
"eval_overall_precision": 0.924812030075188,
"eval_overall_recall": 0.9271356783919598,
"eval_runtime": 0.6284,
"eval_samples_per_second": 270.534,
"eval_steps_per_second": 4.774,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.40208709239959717,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0083,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9174311926605505,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.8982035928143712,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.059115417301654816,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9345088161209069,
"eval_overall_precision": 0.9368686868686869,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.634,
"eval_samples_per_second": 268.135,
"eval_steps_per_second": 4.732,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.41926828026771545,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0081,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9151515151515152,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05649251490831375,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9323308270676693,
"eval_overall_precision": 0.93,
"eval_overall_recall": 0.9346733668341709,
"eval_runtime": 0.6322,
"eval_samples_per_second": 268.904,
"eval_steps_per_second": 4.745,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.42865490913391113,
"learning_rate": 3e-06,
"loss": 0.0083,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.8877551020408163,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05432727560400963,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9296482412060302,
"eval_overall_precision": 0.9296482412060302,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6361,
"eval_samples_per_second": 267.255,
"eval_steps_per_second": 4.716,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.28145793080329895,
"learning_rate": 2.5e-06,
"loss": 0.0084,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9081632653061226,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8725490196078431,
"eval_LOCATION_recall": 0.9468085106382979,
"eval_ORGANIZATION_f1": 0.9123867069486405,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9207317073170732,
"eval_ORGANIZATION_recall": 0.9041916167664671,
"eval_PERSON_f1": 0.988929889298893,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 1.0,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05155736580491066,
"eval_overall_accuracy": 0.987292817679558,
"eval_overall_f1": 0.93734335839599,
"eval_overall_precision": 0.935,
"eval_overall_recall": 0.9396984924623115,
"eval_runtime": 0.6338,
"eval_samples_per_second": 268.23,
"eval_steps_per_second": 4.733,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 1.0425366163253784,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0089,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.8979591836734694,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05201612412929535,
"eval_overall_accuracy": 0.9867403314917127,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9275,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6313,
"eval_samples_per_second": 269.269,
"eval_steps_per_second": 4.752,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.5750377178192139,
"learning_rate": 1.5e-06,
"loss": 0.0076,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.0527535155415535,
"eval_overall_accuracy": 0.9864640883977901,
"eval_overall_f1": 0.9286608260325407,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6284,
"eval_samples_per_second": 270.51,
"eval_steps_per_second": 4.774,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.24895033240318298,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0091,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9141104294478528,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.05304776504635811,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9261576971214018,
"eval_overall_precision": 0.9226932668329177,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6361,
"eval_samples_per_second": 267.243,
"eval_steps_per_second": 4.716,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.4578407108783722,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0089,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.9361702127659575,
"eval_ORGANIZATION_f1": 0.905775075987842,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.052803196012973785,
"eval_overall_accuracy": 0.9861878453038674,
"eval_overall_f1": 0.9298245614035087,
"eval_overall_precision": 0.9275,
"eval_overall_recall": 0.9321608040201005,
"eval_runtime": 0.6603,
"eval_samples_per_second": 257.454,
"eval_steps_per_second": 4.543,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.3821682035923004,
"learning_rate": 0.0,
"loss": 0.0083,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.883248730964467,
"eval_LOCATION_number": 94,
"eval_LOCATION_precision": 0.8446601941747572,
"eval_LOCATION_recall": 0.925531914893617,
"eval_ORGANIZATION_f1": 0.905775075987842,
"eval_ORGANIZATION_number": 167,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8922155688622755,
"eval_PERSON_f1": 0.9852941176470589,
"eval_PERSON_number": 137,
"eval_PERSON_precision": 0.9925925925925926,
"eval_PERSON_recall": 0.9781021897810219,
"eval_loss": 0.053002458065748215,
"eval_overall_accuracy": 0.9859116022099448,
"eval_overall_f1": 0.9273182957393483,
"eval_overall_precision": 0.925,
"eval_overall_recall": 0.9296482412060302,
"eval_runtime": 0.6939,
"eval_samples_per_second": 245.002,
"eval_steps_per_second": 4.324,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4297274884593540.0,
"train_loss": 0.038304175455123185,
"train_runtime": 1085.9964,
"train_samples_per_second": 140.884,
"train_steps_per_second": 8.84
}
],
"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
}