nerui-pt-pl5-1 / trainer_state.json
apwic's picture
End of training
ccfb8ae verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"eval_steps": 500,
"global_step": 9600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.0622260570526123,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8931,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.01694915254237288,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.5,
"eval_LOCATION_recall": 0.008620689655172414,
"eval_ORGANIZATION_f1": 0.24025974025974026,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.24666666666666667,
"eval_ORGANIZATION_recall": 0.23417721518987342,
"eval_PERSON_f1": 0.2660098522167488,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.34177215189873417,
"eval_PERSON_recall": 0.21774193548387097,
"eval_loss": 0.402089387178421,
"eval_overall_accuracy": 0.8597309909415317,
"eval_overall_f1": 0.20667726550079493,
"eval_overall_precision": 0.2813852813852814,
"eval_overall_recall": 0.16331658291457288,
"eval_runtime": 0.2477,
"eval_samples_per_second": 686.279,
"eval_steps_per_second": 12.111,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 1.0000041723251343,
"learning_rate": 4.9e-05,
"loss": 0.3656,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.4267782426778242,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.4146341463414634,
"eval_LOCATION_recall": 0.4396551724137931,
"eval_ORGANIZATION_f1": 0.5901639344262295,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.6122448979591837,
"eval_ORGANIZATION_recall": 0.569620253164557,
"eval_PERSON_f1": 0.5222929936305734,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.43157894736842106,
"eval_PERSON_recall": 0.6612903225806451,
"eval_loss": 0.21696880459785461,
"eval_overall_accuracy": 0.9264342574800988,
"eval_overall_f1": 0.5198135198135198,
"eval_overall_precision": 0.48478260869565215,
"eval_overall_recall": 0.5603015075376885,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.523,
"eval_steps_per_second": 12.38,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.8752551674842834,
"learning_rate": 4.85e-05,
"loss": 0.2175,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7214611872146118,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7669902912621359,
"eval_LOCATION_recall": 0.6810344827586207,
"eval_ORGANIZATION_f1": 0.7411764705882353,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.6923076923076923,
"eval_ORGANIZATION_recall": 0.7974683544303798,
"eval_PERSON_f1": 0.9416342412451362,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9097744360902256,
"eval_PERSON_recall": 0.9758064516129032,
"eval_loss": 0.11590560525655746,
"eval_overall_accuracy": 0.9648641229755696,
"eval_overall_f1": 0.7990196078431372,
"eval_overall_precision": 0.7799043062200957,
"eval_overall_recall": 0.8190954773869347,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.326,
"eval_steps_per_second": 12.394,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.105630874633789,
"learning_rate": 4.8e-05,
"loss": 0.152,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8421052631578948,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.7938931297709924,
"eval_LOCATION_recall": 0.896551724137931,
"eval_ORGANIZATION_f1": 0.812121212121212,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.7790697674418605,
"eval_ORGANIZATION_recall": 0.8481012658227848,
"eval_PERSON_f1": 0.9647058823529411,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9389312977099237,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.08956436812877655,
"eval_overall_accuracy": 0.9706286027998902,
"eval_overall_f1": 0.8677884615384615,
"eval_overall_precision": 0.8317972350230415,
"eval_overall_recall": 0.907035175879397,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.575,
"eval_steps_per_second": 12.345,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.8573193550109863,
"learning_rate": 4.75e-05,
"loss": 0.1153,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8869565217391304,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8947368421052632,
"eval_LOCATION_recall": 0.8793103448275862,
"eval_ORGANIZATION_f1": 0.8492307692307692,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8263473053892215,
"eval_ORGANIZATION_recall": 0.8734177215189873,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.06209466606378555,
"eval_overall_accuracy": 0.9777655778204777,
"eval_overall_f1": 0.8982630272952854,
"eval_overall_precision": 0.8872549019607843,
"eval_overall_recall": 0.9095477386934674,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.706,
"eval_steps_per_second": 12.365,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 2.2799108028411865,
"learning_rate": 4.7e-05,
"loss": 0.1017,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8806584362139918,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.84251968503937,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.8827160493827162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.8614457831325302,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04618193209171295,
"eval_overall_accuracy": 0.9846280538018117,
"eval_overall_f1": 0.9130966952264383,
"eval_overall_precision": 0.8902147971360382,
"eval_overall_recall": 0.9371859296482412,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.771,
"eval_steps_per_second": 12.367,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.5819811820983887,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.0877,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.9170305676855894,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9292035398230089,
"eval_LOCATION_recall": 0.9051724137931034,
"eval_ORGANIZATION_f1": 0.9164086687306501,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.896969696969697,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04141335189342499,
"eval_overall_accuracy": 0.9857260499588252,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.0,
"eval_steps_per_second": 12.371,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 1.0621719360351562,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0772,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.9152542372881356,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.91875,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9074074074074074,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03698663040995598,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9379652605459057,
"eval_overall_precision": 0.9264705882352942,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.264,
"eval_steps_per_second": 12.358,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.5991101861000061,
"learning_rate": 4.55e-05,
"loss": 0.0747,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.9288702928870294,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9024390243902439,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9345794392523364,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04177405312657356,
"eval_overall_accuracy": 0.9860005489980785,
"eval_overall_f1": 0.9493201483312732,
"eval_overall_precision": 0.9343065693430657,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.484,
"eval_steps_per_second": 12.379,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.7477170825004578,
"learning_rate": 4.5e-05,
"loss": 0.0712,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9268292682926829,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8769230769230769,
"eval_LOCATION_recall": 0.9827586206896551,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04179945960640907,
"eval_overall_accuracy": 0.9851770518803185,
"eval_overall_f1": 0.9468479604449939,
"eval_overall_precision": 0.9318734793187348,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.957,
"eval_steps_per_second": 12.352,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.4425092041492462,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0645,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9191489361702128,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.907563025210084,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9341692789968652,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.034665558487176895,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.946450809464508,
"eval_overall_precision": 0.9382716049382716,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.774,
"eval_steps_per_second": 12.349,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.994752824306488,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0594,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9152542372881356,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9164086687306501,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.896969696969697,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03453850373625755,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9392812887236679,
"eval_overall_precision": 0.9266503667481663,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.803,
"eval_steps_per_second": 12.332,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 0.3863960802555084,
"learning_rate": 4.35e-05,
"loss": 0.0584,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.927038626609442,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9496855345911951,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9556962025316456,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.030687231570482254,
"eval_overall_accuracy": 0.9906670326653857,
"eval_overall_f1": 0.9538077403245941,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.612,
"eval_steps_per_second": 12.381,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.7108584642410278,
"learning_rate": 4.3e-05,
"loss": 0.0533,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9276595744680851,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9159663865546218,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9245283018867925,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.91875,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03466002270579338,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.245,
"eval_samples_per_second": 694.012,
"eval_steps_per_second": 12.247,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.4726468324661255,
"learning_rate": 4.25e-05,
"loss": 0.051,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9337539432176657,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03434712067246437,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9514321295143213,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.91,
"eval_steps_per_second": 12.351,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.5781874060630798,
"learning_rate": 4.2e-05,
"loss": 0.0498,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9243697478991596,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9016393442622951,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9196141479099678,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.934640522875817,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03455718606710434,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.89,
"eval_steps_per_second": 12.333,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.1878691464662552,
"learning_rate": 4.15e-05,
"loss": 0.0452,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.925,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8951612903225806,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9171974522292994,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9230769230769231,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035126231610774994,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9414694894146949,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.995,
"eval_steps_per_second": 12.37,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.7006422877311707,
"learning_rate": 4.1e-05,
"loss": 0.0437,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9282700421940928,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9433962264150944,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035111382603645325,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9527363184079602,
"eval_overall_precision": 0.9433497536945813,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.948,
"eval_steps_per_second": 12.37,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.6293537616729736,
"learning_rate": 4.05e-05,
"loss": 0.0419,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9115044247787611,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9363636363636364,
"eval_LOCATION_recall": 0.8879310344827587,
"eval_ORGANIZATION_f1": 0.9375000000000001,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03315844014286995,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9447236180904522,
"eval_overall_precision": 0.9447236180904522,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.628,
"eval_steps_per_second": 12.382,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.43634268641471863,
"learning_rate": 4e-05,
"loss": 0.0409,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9310344827586207,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9310344827586207,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9254658385093167,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9085365853658537,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035573337227106094,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.945273631840796,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.581,
"eval_steps_per_second": 12.363,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 1.104005217552185,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0403,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.925,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8951612903225806,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.02913746051490307,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.518,
"eval_steps_per_second": 12.38,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.9109427332878113,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0368,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9304347826086956,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9385964912280702,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9337539432176657,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03580503910779953,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9473684210526316,
"eval_overall_precision": 0.945,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.269,
"eval_steps_per_second": 12.358,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.4533730745315552,
"learning_rate": 3.85e-05,
"loss": 0.0402,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9531914893617022,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9337539432176657,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9308176100628931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.02975594624876976,
"eval_overall_accuracy": 0.9903925336261323,
"eval_overall_f1": 0.9551122194513715,
"eval_overall_precision": 0.948019801980198,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.141,
"eval_steps_per_second": 12.408,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 0.4602113962173462,
"learning_rate": 3.8e-05,
"loss": 0.0353,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03227541968226433,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2439,
"eval_samples_per_second": 696.954,
"eval_steps_per_second": 12.299,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.7048800587654114,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0332,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9456066945606694,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9186991869918699,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9003215434083601,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9150326797385621,
"eval_ORGANIZATION_recall": 0.8860759493670886,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03731263801455498,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.288,
"eval_steps_per_second": 12.358,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.6570234894752502,
"learning_rate": 3.7e-05,
"loss": 0.0343,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9211356466876972,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9182389937106918,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.040523938834667206,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.468,
"eval_steps_per_second": 12.379,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.9857751131057739,
"learning_rate": 3.65e-05,
"loss": 0.0342,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03457554057240486,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.951310861423221,
"eval_overall_precision": 0.9454094292803971,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.06,
"eval_steps_per_second": 12.389,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.46330365538597107,
"learning_rate": 3.6e-05,
"loss": 0.032,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9152542372881356,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04411082714796066,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9436795994993743,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.003,
"eval_steps_per_second": 12.406,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.4757544696331024,
"learning_rate": 3.55e-05,
"loss": 0.0275,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9396551724137931,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9396551724137931,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9221183800623053,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9079754601226994,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04470400512218475,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.55,
"eval_steps_per_second": 12.398,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 1.0357615947723389,
"learning_rate": 3.5e-05,
"loss": 0.0273,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9304347826086956,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9385964912280702,
"eval_LOCATION_recall": 0.9224137931034483,
"eval_ORGANIZATION_f1": 0.9316770186335404,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9146341463414634,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.043819691985845566,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9488139825218478,
"eval_overall_precision": 0.9429280397022333,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.271,
"eval_steps_per_second": 12.393,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.5754586458206177,
"learning_rate": 3.45e-05,
"loss": 0.0287,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9411764705882353,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9180327868852459,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9290322580645162,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9473684210526315,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.035712841898202896,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9498746867167919,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.469,
"eval_steps_per_second": 12.397,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.4603827893733978,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0274,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9288702928870294,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9024390243902439,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9131832797427653,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9281045751633987,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04034664109349251,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.94,
"eval_overall_precision": 0.9353233830845771,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.177,
"eval_steps_per_second": 12.409,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.4669646620750427,
"learning_rate": 3.35e-05,
"loss": 0.0284,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9327731092436975,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9098360655737705,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9196141479099678,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.934640522875817,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04073726758360863,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9436795994993743,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.664,
"eval_steps_per_second": 12.365,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.14242352545261383,
"learning_rate": 3.3e-05,
"loss": 0.0269,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9312499999999999,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04001469165086746,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9515527950310558,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.955,
"eval_steps_per_second": 12.334,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.5518023371696472,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0245,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.935064935064935,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9391304347826087,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9226006191950465,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9030303030303031,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03874511644244194,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.945273631840796,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.42,
"eval_steps_per_second": 12.343,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 1.2177473306655884,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0251,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9308176100628932,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.925,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03678901121020317,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9514321295143213,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.694,
"eval_steps_per_second": 12.383,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 1.4173684120178223,
"learning_rate": 3.15e-05,
"loss": 0.0243,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9356223175965666,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9316239316239316,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9333333333333332,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9363057324840764,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03889763355255127,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2444,
"eval_samples_per_second": 695.549,
"eval_steps_per_second": 12.274,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.6296694874763489,
"learning_rate": 3.1e-05,
"loss": 0.0242,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9113924050632911,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8925619834710744,
"eval_LOCATION_recall": 0.9310344827586207,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04012976959347725,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.989,
"eval_steps_per_second": 12.353,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.07241743803024292,
"learning_rate": 3.05e-05,
"loss": 0.0244,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04065397381782532,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.128,
"eval_steps_per_second": 12.39,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.13085119426250458,
"learning_rate": 3e-05,
"loss": 0.0211,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9375000000000001,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04333576187491417,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9515527950310558,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.162,
"eval_steps_per_second": 12.356,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.029861435294151306,
"learning_rate": 2.95e-05,
"loss": 0.0223,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9278996865203761,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03654933720827103,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.253,
"eval_steps_per_second": 12.375,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.09470277279615402,
"learning_rate": 2.9e-05,
"loss": 0.0224,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.94017094017094,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9322033898305084,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9278996865203761,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9192546583850931,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.039208512753248215,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9489414694894147,
"eval_overall_precision": 0.9407407407407408,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.592,
"eval_steps_per_second": 12.381,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.29208576679229736,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0197,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9316239316239315,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.923728813559322,
"eval_LOCATION_recall": 0.9396551724137931,
"eval_ORGANIZATION_f1": 0.9274447949526813,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9245283018867925,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03720787167549133,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.453,
"eval_steps_per_second": 12.396,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.3295332193374634,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.022,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9177215189873418,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9177215189873418,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04005124792456627,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9451371571072318,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.36,
"eval_steps_per_second": 12.359,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 1.0696682929992676,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0192,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04148309305310249,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.317,
"eval_steps_per_second": 12.376,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.5310882925987244,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0197,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9456066945606694,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9186991869918699,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9274447949526813,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9245283018867925,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03862782195210457,
"eval_overall_accuracy": 0.990118034586879,
"eval_overall_f1": 0.9503722084367245,
"eval_overall_precision": 0.9387254901960784,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.028,
"eval_steps_per_second": 12.318,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.36547964811325073,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.02,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.940809968847352,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9556962025316456,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.042170971632003784,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9540372670807453,
"eval_overall_precision": 0.9434889434889435,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.197,
"eval_steps_per_second": 12.303,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.4364250600337982,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0192,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9411764705882353,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9180327868852459,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.935064935064935,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.03884365037083626,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.424,
"eval_steps_per_second": 12.431,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.6926938891410828,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0182,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9535864978902953,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9338842975206612,
"eval_LOCATION_recall": 0.9741379310344828,
"eval_ORGANIZATION_f1": 0.9430379746835443,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04192095994949341,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9600997506234414,
"eval_overall_precision": 0.9529702970297029,
"eval_overall_recall": 0.9673366834170855,
"eval_runtime": 0.2413,
"eval_samples_per_second": 704.587,
"eval_steps_per_second": 12.434,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.5129674673080444,
"learning_rate": 2.5e-05,
"loss": 0.0182,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9491525423728815,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9142857142857144,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9171974522292994,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04355218634009361,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9451371571072318,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.06,
"eval_steps_per_second": 12.389,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.3724958598613739,
"learning_rate": 2.45e-05,
"loss": 0.0196,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04640508443117142,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.373,
"eval_steps_per_second": 12.377,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.4651976525783539,
"learning_rate": 2.4e-05,
"loss": 0.016,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9288702928870294,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9024390243902439,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.935064935064935,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04982294142246246,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9414694894146949,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2422,
"eval_samples_per_second": 702.013,
"eval_steps_per_second": 12.388,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.3692150413990021,
"learning_rate": 2.35e-05,
"loss": 0.0174,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9426751592356688,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9487179487179487,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.047746025025844574,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.203,
"eval_steps_per_second": 12.409,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 2.322037935256958,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0156,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05073067173361778,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.172,
"eval_steps_per_second": 12.409,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.8182074427604675,
"learning_rate": 2.25e-05,
"loss": 0.0161,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04936642944812775,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9473684210526316,
"eval_overall_precision": 0.945,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.981,
"eval_steps_per_second": 12.388,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.47536519169807434,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0154,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9177215189873418,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9177215189873418,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04633556678891182,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.149,
"eval_steps_per_second": 12.391,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.4734033942222595,
"learning_rate": 2.15e-05,
"loss": 0.0159,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9482758620689655,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9482758620689655,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9245283018867925,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.91875,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04754474759101868,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.32,
"eval_steps_per_second": 12.376,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.09098278731107712,
"learning_rate": 2.1e-05,
"loss": 0.0159,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9327731092436975,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9098360655737705,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9260450160771704,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9411764705882353,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.049943216145038605,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9461827284105131,
"eval_overall_precision": 0.942643391521197,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.712,
"eval_steps_per_second": 12.383,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.28300827741622925,
"learning_rate": 2.05e-05,
"loss": 0.0154,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04638950154185295,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.998,
"eval_steps_per_second": 12.388,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.24135783314704895,
"learning_rate": 2e-05,
"loss": 0.0146,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9372384937238494,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9105691056910569,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9396825396825397,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9426751592356688,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05022583156824112,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9515527950310558,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.9623115577889447,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.667,
"eval_steps_per_second": 12.382,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.48841485381126404,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0164,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9411764705882353,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9180327868852459,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.047981929033994675,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.864,
"eval_steps_per_second": 12.386,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.623166024684906,
"learning_rate": 1.9e-05,
"loss": 0.0126,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.925,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.8951612903225806,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9102564102564102,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.922077922077922,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05383405089378357,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9376558603491272,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.589,
"eval_steps_per_second": 12.399,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.06195319816470146,
"learning_rate": 1.85e-05,
"loss": 0.0142,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9572649572649573,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9491525423728814,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.9206349206349206,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9235668789808917,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9879518072289156,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.984,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050431687384843826,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2441,
"eval_samples_per_second": 696.509,
"eval_steps_per_second": 12.291,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.38351964950561523,
"learning_rate": 1.8e-05,
"loss": 0.0131,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9568965517241379,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9568965517241379,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9463722397476341,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9433962264150944,
"eval_ORGANIZATION_recall": 0.9493670886075949,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04740133136510849,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.96,
"eval_overall_precision": 0.9552238805970149,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.471,
"eval_steps_per_second": 12.397,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.42032256722450256,
"learning_rate": 1.75e-05,
"loss": 0.0144,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9451476793248945,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9256198347107438,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9799196787148594,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.976,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05012889206409454,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.183,
"eval_steps_per_second": 12.356,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.6347458362579346,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0135,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9240506329113924,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05208972468972206,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.867,
"eval_steps_per_second": 12.351,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 1.0222524404525757,
"learning_rate": 1.65e-05,
"loss": 0.0162,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9201277955271565,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9290322580645162,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05340787023305893,
"eval_overall_accuracy": 0.9862750480373319,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.351,
"eval_steps_per_second": 12.412,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.6841771006584167,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0136,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05373825877904892,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9525,
"eval_overall_precision": 0.9477611940298507,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.784,
"eval_steps_per_second": 12.402,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 1.1261268854141235,
"learning_rate": 1.55e-05,
"loss": 0.0138,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05131537467241287,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.951188986232791,
"eval_overall_precision": 0.9476309226932669,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.112,
"eval_steps_per_second": 12.39,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.47885391116142273,
"learning_rate": 1.5e-05,
"loss": 0.0135,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05541845038533211,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9476309226932669,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.621,
"eval_steps_per_second": 12.364,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.29839274287223816,
"learning_rate": 1.45e-05,
"loss": 0.0121,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9482758620689655,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9482758620689655,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9341692789968652,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.9430379746835443,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05237449333071709,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9538077403245941,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.886,
"eval_steps_per_second": 12.333,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 1.4181568622589111,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0131,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05246526002883911,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.097,
"eval_steps_per_second": 12.39,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 0.5246819853782654,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0129,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9322033898305084,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05284268409013748,
"eval_overall_accuracy": 0.9876475432335987,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.026,
"eval_steps_per_second": 12.371,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.1629040539264679,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0118,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9361702127659575,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9243697478991597,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9329073482428115,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9419354838709677,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05083697289228439,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9461827284105131,
"eval_overall_precision": 0.942643391521197,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.535,
"eval_steps_per_second": 12.415,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.34347105026245117,
"learning_rate": 1.25e-05,
"loss": 0.0109,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9682539682539683,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.953125,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.053751371800899506,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.067,
"eval_steps_per_second": 12.389,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.0426780991256237,
"learning_rate": 1.2e-05,
"loss": 0.0115,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9294871794871796,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9415584415584416,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9682539682539683,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.953125,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05429477617144585,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9438202247191011,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2446,
"eval_samples_per_second": 695.028,
"eval_steps_per_second": 12.265,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.332469642162323,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0121,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9201277955271565,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9290322580645162,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05492376908659935,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9413233458177278,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.433,
"eval_steps_per_second": 12.396,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.5249147415161133,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0116,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9044585987261147,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9102564102564102,
"eval_ORGANIZATION_recall": 0.8987341772151899,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05314483493566513,
"eval_overall_accuracy": 0.9862750480373319,
"eval_overall_f1": 0.9351620947630923,
"eval_overall_precision": 0.9282178217821783,
"eval_overall_recall": 0.9422110552763819,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.87,
"eval_steps_per_second": 12.333,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.028825916349887848,
"learning_rate": 1.05e-05,
"loss": 0.0131,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.944206008583691,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9401709401709402,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9526813880126183,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.949685534591195,
"eval_ORGANIZATION_recall": 0.9556962025316456,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.04911971837282181,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.958801498127341,
"eval_overall_precision": 0.9528535980148883,
"eval_overall_recall": 0.964824120603015,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.29,
"eval_steps_per_second": 12.323,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.19487972557544708,
"learning_rate": 1e-05,
"loss": 0.0113,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9482758620689655,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9482758620689655,
"eval_LOCATION_recall": 0.9482758620689655,
"eval_ORGANIZATION_f1": 0.9085173501577287,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9056603773584906,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05024532973766327,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9413233458177278,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.107,
"eval_steps_per_second": 12.372,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.2933664619922638,
"learning_rate": 9.5e-06,
"loss": 0.0114,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9142857142857144,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9171974522292994,
"eval_ORGANIZATION_recall": 0.9113924050632911,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.050492897629737854,
"eval_overall_accuracy": 0.9881965413121054,
"eval_overall_f1": 0.9450000000000001,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.245,
"eval_samples_per_second": 693.863,
"eval_steps_per_second": 12.245,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.8371833562850952,
"learning_rate": 9e-06,
"loss": 0.0101,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9137380191693291,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9225806451612903,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9761904761904763,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9609375,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05484500154852867,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9425,
"eval_overall_precision": 0.9378109452736318,
"eval_overall_recall": 0.9472361809045227,
"eval_runtime": 0.2414,
"eval_samples_per_second": 704.348,
"eval_steps_per_second": 12.43,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.3084019720554352,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0098,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.910828025477707,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.9050632911392406,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.0543341189622879,
"eval_overall_accuracy": 0.987098545155092,
"eval_overall_f1": 0.9388264669163546,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9447236180904522,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.604,
"eval_steps_per_second": 12.364,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.04305460304021835,
"learning_rate": 8.000000000000001e-06,
"loss": 0.01,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9527896995708154,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9487179487179487,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.054905395954847336,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9523809523809523,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.305,
"eval_steps_per_second": 12.376,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.7204985022544861,
"learning_rate": 7.5e-06,
"loss": 0.0106,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9491525423728815,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9655172413793104,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05248566344380379,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9501246882793017,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.138,
"eval_steps_per_second": 12.408,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.07470478117465973,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0102,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926984126984127,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9299363057324841,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05321876332163811,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.282,
"eval_steps_per_second": 12.358,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.2286868691444397,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0092,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9206349206349206,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9235668789808917,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.053863525390625,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9426433915211971,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.949748743718593,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.324,
"eval_steps_per_second": 12.341,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.19395892322063446,
"learning_rate": 6e-06,
"loss": 0.0095,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9367088607594937,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9173553719008265,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05385447293519974,
"eval_overall_accuracy": 0.9873730441943454,
"eval_overall_f1": 0.9463171036204745,
"eval_overall_precision": 0.9404466501240695,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.995,
"eval_steps_per_second": 12.37,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.5978826880455017,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0099,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9367088607594937,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9367088607594937,
"eval_ORGANIZATION_recall": 0.9367088607594937,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.052636079490184784,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9526184538653367,
"eval_overall_precision": 0.9455445544554455,
"eval_overall_recall": 0.9597989949748744,
"eval_runtime": 0.2422,
"eval_samples_per_second": 702.032,
"eval_steps_per_second": 12.389,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.17808915674686432,
"learning_rate": 5e-06,
"loss": 0.0095,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9363057324840764,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9423076923076923,
"eval_ORGANIZATION_recall": 0.930379746835443,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05316346138715744,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9536921151439299,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.957286432160804,
"eval_runtime": 0.2434,
"eval_samples_per_second": 698.582,
"eval_steps_per_second": 12.328,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.17433640360832214,
"learning_rate": 4.5e-06,
"loss": 0.0099,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.052069030702114105,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.95,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9547738693467337,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.241,
"eval_steps_per_second": 12.392,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.0391317717730999,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0095,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9240506329113924,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9240506329113924,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.976,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9682539682539683,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05470087379217148,
"eval_overall_accuracy": 0.9879220422728521,
"eval_overall_f1": 0.9451371571072318,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2418,
"eval_samples_per_second": 702.995,
"eval_steps_per_second": 12.406,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 1.2939667701721191,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0096,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9487179487179486,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.940677966101695,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9299363057324842,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9358974358974359,
"eval_ORGANIZATION_recall": 0.9240506329113924,
"eval_PERSON_f1": 0.9721115537848605,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9606299212598425,
"eval_PERSON_recall": 0.9838709677419355,
"eval_loss": 0.05360059067606926,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.744,
"eval_steps_per_second": 12.401,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 1.3997987508773804,
"learning_rate": 3e-06,
"loss": 0.009,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9446808510638298,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.9327731092436975,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9800796812749005,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.968503937007874,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.053766991943120956,
"eval_overall_accuracy": 0.9884710403513588,
"eval_overall_f1": 0.9475,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.867,
"eval_steps_per_second": 12.404,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.015623769722878933,
"learning_rate": 2.5e-06,
"loss": 0.0094,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05312187969684601,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.669,
"eval_steps_per_second": 12.382,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.06812173873186111,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0083,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.9235668789808917,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9294871794871795,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.052705731242895126,
"eval_overall_accuracy": 0.9887455393906122,
"eval_overall_f1": 0.9475,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.06,
"eval_steps_per_second": 12.372,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.13947905600070953,
"learning_rate": 1.5e-06,
"loss": 0.0099,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05367732793092728,
"eval_overall_accuracy": 0.9890200384298655,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.966,
"eval_steps_per_second": 12.352,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.10114230960607529,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0078,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.05298721790313721,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.26,
"eval_steps_per_second": 12.393,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.5689762234687805,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0093,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.052819643169641495,
"eval_overall_accuracy": 0.9892945374691189,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.726,
"eval_steps_per_second": 12.366,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.09888800233602524,
"learning_rate": 0.0,
"loss": 0.0086,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9406779661016949,
"eval_LOCATION_number": 116,
"eval_LOCATION_precision": 0.925,
"eval_LOCATION_recall": 0.9568965517241379,
"eval_ORGANIZATION_f1": 0.926517571884984,
"eval_ORGANIZATION_number": 158,
"eval_ORGANIZATION_precision": 0.9354838709677419,
"eval_ORGANIZATION_recall": 0.9177215189873418,
"eval_PERSON_f1": 0.9840000000000001,
"eval_PERSON_number": 124,
"eval_PERSON_precision": 0.9761904761904762,
"eval_PERSON_recall": 0.9919354838709677,
"eval_loss": 0.052767641842365265,
"eval_overall_accuracy": 0.9895690365083722,
"eval_overall_f1": 0.9486858573216519,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9522613065326633,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.096,
"eval_steps_per_second": 12.372,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4293597283743744.0,
"train_loss": 0.04076442163437605,
"train_runtime": 503.1696,
"train_samples_per_second": 304.271,
"train_steps_per_second": 19.079
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4293597283743744.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}