nerui-pt-pl5-2 / trainer_state.json
apwic's picture
End of training
f38eabd 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": 1.303944706916809,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.881,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.020833333333333336,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.3333333333333333,
"eval_LOCATION_recall": 0.010752688172043012,
"eval_ORGANIZATION_f1": 0.2840909090909091,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.26881720430107525,
"eval_ORGANIZATION_recall": 0.30120481927710846,
"eval_PERSON_f1": 0.32218844984802436,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.28342245989304815,
"eval_PERSON_recall": 0.3732394366197183,
"eval_loss": 0.39615654945373535,
"eval_overall_accuracy": 0.8672153635116598,
"eval_overall_f1": 0.2676962676962677,
"eval_overall_precision": 0.2765957446808511,
"eval_overall_recall": 0.2593516209476309,
"eval_runtime": 0.2484,
"eval_samples_per_second": 684.305,
"eval_steps_per_second": 12.076,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 0.8351965546607971,
"learning_rate": 4.9e-05,
"loss": 0.3506,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.3706896551724138,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.30935251798561153,
"eval_LOCATION_recall": 0.46236559139784944,
"eval_ORGANIZATION_f1": 0.656891495601173,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.64,
"eval_ORGANIZATION_recall": 0.6746987951807228,
"eval_PERSON_f1": 0.7088607594936709,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.6436781609195402,
"eval_PERSON_recall": 0.7887323943661971,
"eval_loss": 0.19686433672904968,
"eval_overall_accuracy": 0.9418381344307271,
"eval_overall_f1": 0.6006749156355455,
"eval_overall_precision": 0.5471311475409836,
"eval_overall_recall": 0.6658354114713217,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.126,
"eval_steps_per_second": 12.373,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 0.8129919767379761,
"learning_rate": 4.85e-05,
"loss": 0.1965,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7045454545454546,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.7469879518072289,
"eval_LOCATION_recall": 0.6666666666666666,
"eval_ORGANIZATION_f1": 0.7512953367875648,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.6590909090909091,
"eval_ORGANIZATION_recall": 0.8734939759036144,
"eval_PERSON_f1": 0.9655172413793103,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9459459459459459,
"eval_PERSON_recall": 0.9859154929577465,
"eval_loss": 0.11103475093841553,
"eval_overall_accuracy": 0.9637860082304527,
"eval_overall_f1": 0.8145539906103286,
"eval_overall_precision": 0.7694013303769401,
"eval_overall_recall": 0.8653366583541147,
"eval_runtime": 0.2454,
"eval_samples_per_second": 692.813,
"eval_steps_per_second": 12.226,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.207106113433838,
"learning_rate": 4.8e-05,
"loss": 0.1379,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.7692307692307692,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.6956521739130435,
"eval_LOCATION_recall": 0.8602150537634409,
"eval_ORGANIZATION_f1": 0.8171428571428571,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.7771739130434783,
"eval_ORGANIZATION_recall": 0.8614457831325302,
"eval_PERSON_f1": 0.9860139860139859,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9791666666666666,
"eval_PERSON_recall": 0.9929577464788732,
"eval_loss": 0.0912475734949112,
"eval_overall_accuracy": 0.9700960219478738,
"eval_overall_f1": 0.8625592417061612,
"eval_overall_precision": 0.8216704288939052,
"eval_overall_recall": 0.9077306733167082,
"eval_runtime": 0.2446,
"eval_samples_per_second": 694.967,
"eval_steps_per_second": 12.264,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.673134446144104,
"learning_rate": 4.75e-05,
"loss": 0.1107,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8481675392670157,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.826530612244898,
"eval_LOCATION_recall": 0.8709677419354839,
"eval_ORGANIZATION_f1": 0.8579710144927536,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8268156424581006,
"eval_ORGANIZATION_recall": 0.891566265060241,
"eval_PERSON_f1": 0.979020979020979,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9722222222222222,
"eval_PERSON_recall": 0.9859154929577465,
"eval_loss": 0.06871715188026428,
"eval_overall_accuracy": 0.9794238683127572,
"eval_overall_f1": 0.8978102189781021,
"eval_overall_precision": 0.8764845605700713,
"eval_overall_recall": 0.9201995012468828,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.696,
"eval_steps_per_second": 12.33,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 1.1874234676361084,
"learning_rate": 4.7e-05,
"loss": 0.0972,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8186046511627908,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.7213114754098361,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.8238993710691823,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8618421052631579,
"eval_ORGANIZATION_recall": 0.7891566265060241,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.07641229778528214,
"eval_overall_accuracy": 0.9758573388203018,
"eval_overall_f1": 0.8763769889840882,
"eval_overall_precision": 0.8605769230769231,
"eval_overall_recall": 0.8927680798004988,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.884,
"eval_steps_per_second": 12.351,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 1.058882236480713,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.086,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.8481675392670157,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.826530612244898,
"eval_LOCATION_recall": 0.8709677419354839,
"eval_ORGANIZATION_f1": 0.8707865168539326,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8157894736842105,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.975609756097561,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9655172413793104,
"eval_PERSON_recall": 0.9859154929577465,
"eval_loss": 0.06198972836136818,
"eval_overall_accuracy": 0.978875171467764,
"eval_overall_f1": 0.9016786570743406,
"eval_overall_precision": 0.8683602771362586,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.466,
"eval_steps_per_second": 12.344,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.5954187512397766,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0786,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8699999999999999,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8130841121495327,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.883720930232558,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8539325842696629,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9787234042553192,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9857142857142858,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0521794930100441,
"eval_overall_accuracy": 0.9835390946502057,
"eval_overall_f1": 0.9128329297820824,
"eval_overall_precision": 0.8870588235294118,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2443,
"eval_samples_per_second": 695.914,
"eval_steps_per_second": 12.281,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.9238722920417786,
"learning_rate": 4.55e-05,
"loss": 0.0709,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.83,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.7757009345794392,
"eval_LOCATION_recall": 0.8924731182795699,
"eval_ORGANIZATION_f1": 0.8685015290519877,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8819875776397516,
"eval_ORGANIZATION_recall": 0.8554216867469879,
"eval_PERSON_f1": 0.9787234042553192,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9857142857142858,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05216008797287941,
"eval_overall_accuracy": 0.9807956104252401,
"eval_overall_f1": 0.8974042027194067,
"eval_overall_precision": 0.8897058823529411,
"eval_overall_recall": 0.9052369077306733,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.495,
"eval_steps_per_second": 12.344,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.8774165511131287,
"learning_rate": 4.5e-05,
"loss": 0.0665,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.8484848484848486,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8,
"eval_LOCATION_recall": 0.9032258064516129,
"eval_ORGANIZATION_f1": 0.9053254437869822,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8895348837209303,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.049419909715652466,
"eval_overall_accuracy": 0.9838134430727024,
"eval_overall_f1": 0.9159561510353227,
"eval_overall_precision": 0.8952380952380953,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2434,
"eval_samples_per_second": 698.366,
"eval_steps_per_second": 12.324,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.4000283479690552,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.0598,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.8717948717948718,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.9139784946236559,
"eval_ORGANIZATION_f1": 0.9,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8793103448275862,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.048907868564128876,
"eval_overall_accuracy": 0.9838134430727024,
"eval_overall_f1": 0.9193154034229828,
"eval_overall_precision": 0.9016786570743405,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.879,
"eval_steps_per_second": 12.333,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.5166382193565369,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0584,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.875,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8484848484848485,
"eval_LOCATION_recall": 0.9032258064516129,
"eval_ORGANIZATION_f1": 0.9026548672566371,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.884393063583815,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05024115741252899,
"eval_overall_accuracy": 0.9849108367626886,
"eval_overall_f1": 0.9202453987730063,
"eval_overall_precision": 0.9057971014492754,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.208,
"eval_steps_per_second": 12.374,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 1.316857933998108,
"learning_rate": 4.35e-05,
"loss": 0.0536,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.8900523560209423,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8673469387755102,
"eval_LOCATION_recall": 0.9139784946236559,
"eval_ORGANIZATION_f1": 0.9024390243902438,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9135802469135802,
"eval_ORGANIZATION_recall": 0.891566265060241,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05017678812146187,
"eval_overall_accuracy": 0.9854595336076818,
"eval_overall_f1": 0.9251870324189526,
"eval_overall_precision": 0.9251870324189526,
"eval_overall_recall": 0.9251870324189526,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.251,
"eval_steps_per_second": 12.41,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.3580028712749481,
"learning_rate": 4.3e-05,
"loss": 0.0519,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9090909090909091,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9042553191489362,
"eval_LOCATION_recall": 0.9139784946236559,
"eval_ORGANIZATION_f1": 0.9085365853658537,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9197530864197531,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.05272529274225235,
"eval_overall_accuracy": 0.9854595336076818,
"eval_overall_f1": 0.9336670838548186,
"eval_overall_precision": 0.9371859296482412,
"eval_overall_recall": 0.9301745635910225,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.276,
"eval_steps_per_second": 12.375,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.4127146303653717,
"learning_rate": 4.25e-05,
"loss": 0.0507,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.91131498470948,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.04498204216361046,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.9339975093399752,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.459,
"eval_steps_per_second": 12.308,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.8430036902427673,
"learning_rate": 4.2e-05,
"loss": 0.0451,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.8923076923076922,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8529411764705882,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9207317073170733,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9320987654320988,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.04584517329931259,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9318463444857497,
"eval_overall_precision": 0.9261083743842364,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.167,
"eval_steps_per_second": 12.303,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.39217910170555115,
"learning_rate": 4.15e-05,
"loss": 0.0438,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.8888888888888888,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8380952380952381,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9141104294478528,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.93125,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0515635646879673,
"eval_overall_accuracy": 0.9860082304526749,
"eval_overall_f1": 0.9270704573547589,
"eval_overall_precision": 0.9191176470588235,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2436,
"eval_samples_per_second": 697.894,
"eval_steps_per_second": 12.316,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.29842302203178406,
"learning_rate": 4.1e-05,
"loss": 0.0415,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9052631578947367,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8865979381443299,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9030303030303031,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9085365853658537,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.04907821863889694,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9267080745341615,
"eval_overall_precision": 0.9232673267326733,
"eval_overall_recall": 0.9301745635910225,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.691,
"eval_steps_per_second": 12.33,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.5437675714492798,
"learning_rate": 4.05e-05,
"loss": 0.04,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9297297297297297,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9347826086956522,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9221556886227544,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.04814886674284935,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.969,
"eval_steps_per_second": 12.388,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.3828229308128357,
"learning_rate": 4e-05,
"loss": 0.0383,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9368421052631579,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9175257731958762,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9365558912386707,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.050097767263650894,
"eval_overall_accuracy": 0.9890260631001372,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9526184538653366,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.529,
"eval_steps_per_second": 12.345,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.8633430004119873,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0391,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.8934010152284263,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8461538461538461,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.91131498470948,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9254658385093167,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05232459306716919,
"eval_overall_accuracy": 0.9860082304526749,
"eval_overall_f1": 0.9282178217821783,
"eval_overall_precision": 0.9213759213759214,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2415,
"eval_samples_per_second": 703.824,
"eval_steps_per_second": 12.42,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.5940188765525818,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0353,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9214659685863874,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9313432835820897,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9230769230769231,
"eval_ORGANIZATION_recall": 0.9397590361445783,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.04511262848973274,
"eval_overall_accuracy": 0.9890260631001372,
"eval_overall_f1": 0.9443757725587144,
"eval_overall_precision": 0.9362745098039216,
"eval_overall_recall": 0.9526184538653366,
"eval_runtime": 0.2439,
"eval_samples_per_second": 697.017,
"eval_steps_per_second": 12.3,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.4868105947971344,
"learning_rate": 3.85e-05,
"loss": 0.0356,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.049014270305633545,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9369592088998765,
"eval_overall_precision": 0.928921568627451,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.43,
"eval_steps_per_second": 12.361,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 1.0751893520355225,
"learning_rate": 3.8e-05,
"loss": 0.0333,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9081632653061223,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8640776699029126,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9546827794561934,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9575757575757575,
"eval_ORGANIZATION_recall": 0.9518072289156626,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.049128565937280655,
"eval_overall_accuracy": 0.988477366255144,
"eval_overall_f1": 0.9494451294697903,
"eval_overall_precision": 0.9390243902439024,
"eval_overall_recall": 0.9600997506234414,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.765,
"eval_steps_per_second": 12.349,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.47952502965927124,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.033,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9270833333333334,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9123867069486404,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05440696328878403,
"eval_overall_accuracy": 0.9851851851851852,
"eval_overall_f1": 0.9368029739776952,
"eval_overall_precision": 0.9310344827586207,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.463,
"eval_steps_per_second": 12.379,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.10115259140729904,
"learning_rate": 3.7e-05,
"loss": 0.0333,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9247311827956989,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9247311827956989,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9365558912386707,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05545302480459213,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9451371571072319,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.819,
"eval_steps_per_second": 12.385,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 1.5346511602401733,
"learning_rate": 3.65e-05,
"loss": 0.0309,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9319371727748691,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9361702127659575,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9447852760736196,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.05618004500865936,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.9502487562189055,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9526184538653366,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.519,
"eval_steps_per_second": 12.38,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.23140467703342438,
"learning_rate": 3.6e-05,
"loss": 0.0311,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.8756756756756756,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8804347826086957,
"eval_LOCATION_recall": 0.8709677419354839,
"eval_ORGANIZATION_f1": 0.9058823529411766,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8850574712643678,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9716312056737589,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9785714285714285,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.054653264582157135,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9219330855018587,
"eval_overall_precision": 0.916256157635468,
"eval_overall_recall": 0.9276807980049875,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.217,
"eval_steps_per_second": 12.339,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 3.1744093894958496,
"learning_rate": 3.55e-05,
"loss": 0.0272,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.8979591836734693,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.901840490797546,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.91875,
"eval_ORGANIZATION_recall": 0.8855421686746988,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.05426659807562828,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9242236024844721,
"eval_overall_precision": 0.9207920792079208,
"eval_overall_recall": 0.9276807980049875,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.471,
"eval_steps_per_second": 12.379,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.6167053580284119,
"learning_rate": 3.5e-05,
"loss": 0.0257,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.8842105263157894,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.865979381443299,
"eval_LOCATION_recall": 0.9032258064516129,
"eval_ORGANIZATION_f1": 0.896551724137931,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8571428571428571,
"eval_ORGANIZATION_recall": 0.9397590361445783,
"eval_PERSON_f1": 0.9823321554770318,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9858156028368794,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.058896344155073166,
"eval_overall_accuracy": 0.9843621399176955,
"eval_overall_f1": 0.9232643118148599,
"eval_overall_precision": 0.9023809523809524,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2432,
"eval_samples_per_second": 699.135,
"eval_steps_per_second": 12.338,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.19404320418834686,
"learning_rate": 3.45e-05,
"loss": 0.0263,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9312169312169313,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9300911854103343,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05474191531538963,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9463171036204744,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.244,
"eval_samples_per_second": 696.617,
"eval_steps_per_second": 12.293,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 0.8469938635826111,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0271,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9319371727748691,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9081632653061225,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9268292682926829,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9382716049382716,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.05311959236860275,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9440993788819876,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.614,
"eval_steps_per_second": 12.381,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.771607518196106,
"learning_rate": 3.35e-05,
"loss": 0.0271,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9235474006116209,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.937888198757764,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.05019374191761017,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.940149625935162,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.074,
"eval_steps_per_second": 12.319,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.3017832040786743,
"learning_rate": 3.3e-05,
"loss": 0.0255,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.922279792746114,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.89,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9393939393939394,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9451219512195121,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06320970505475998,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9480198019801981,
"eval_overall_precision": 0.941031941031941,
"eval_overall_recall": 0.9551122194513716,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.997,
"eval_steps_per_second": 12.371,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.43580183386802673,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0235,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9166666666666667,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9365558912386707,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9616724738675958,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9517241379310345,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0591592974960804,
"eval_overall_accuracy": 0.9862825788751715,
"eval_overall_f1": 0.9407407407407408,
"eval_overall_precision": 0.9315403422982885,
"eval_overall_recall": 0.9501246882793017,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.127,
"eval_steps_per_second": 12.39,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.4252844750881195,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0243,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9137055837563453,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8653846153846154,
"eval_LOCATION_recall": 0.967741935483871,
"eval_ORGANIZATION_f1": 0.9353846153846154,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9559748427672956,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0575077161192894,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9417596034696407,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.186,
"eval_steps_per_second": 12.409,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 1.1876208782196045,
"learning_rate": 3.15e-05,
"loss": 0.0225,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9214659685863874,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.906906906906907,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9686411149825783,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9586206896551724,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.058609604835510254,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9321824907521579,
"eval_overall_precision": 0.9219512195121952,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.662,
"eval_steps_per_second": 12.312,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.12291021645069122,
"learning_rate": 3.1e-05,
"loss": 0.0239,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9157894736842105,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.04954139515757561,
"eval_overall_accuracy": 0.988477366255144,
"eval_overall_f1": 0.9416149068322982,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2425,
"eval_samples_per_second": 700.96,
"eval_steps_per_second": 12.37,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.7959946990013123,
"learning_rate": 3.05e-05,
"loss": 0.0202,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.923076923076923,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8823529411764706,
"eval_LOCATION_recall": 0.967741935483871,
"eval_ORGANIZATION_f1": 0.9263803680981595,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9788732394366197,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9788732394366197,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.053312622010707855,
"eval_overall_accuracy": 0.9890260631001372,
"eval_overall_f1": 0.9440993788819876,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.159,
"eval_steps_per_second": 12.356,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.5897502899169922,
"learning_rate": 3e-05,
"loss": 0.0199,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9148936170212766,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9052631578947369,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9614035087719298,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.958041958041958,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.054748691618442535,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.9366459627329192,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.513,
"eval_steps_per_second": 12.309,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 0.09413298219442368,
"learning_rate": 2.95e-05,
"loss": 0.0219,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9042553191489361,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8947368421052632,
"eval_LOCATION_recall": 0.9139784946236559,
"eval_ORGANIZATION_f1": 0.9253731343283581,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.05619138851761818,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9381188118811881,
"eval_overall_precision": 0.9312039312039312,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2416,
"eval_samples_per_second": 703.637,
"eval_steps_per_second": 12.417,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.1863897740840912,
"learning_rate": 2.9e-05,
"loss": 0.0209,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9166666666666667,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9263803680981595,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.94375,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.0575493648648262,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.941469489414695,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.614,
"eval_steps_per_second": 12.381,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.30863094329833984,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0188,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9214659685863874,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9244712990936556,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.059022873640060425,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9405940594059405,
"eval_overall_precision": 0.9336609336609336,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.346,
"eval_steps_per_second": 12.394,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 0.6253886222839355,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0209,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.894736842105263,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8762886597938144,
"eval_LOCATION_recall": 0.9139784946236559,
"eval_ORGANIZATION_f1": 0.8961424332344213,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8830409356725146,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9752650176678446,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9787234042553191,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05520622059702873,
"eval_overall_accuracy": 0.9854595336076818,
"eval_overall_f1": 0.9234567901234567,
"eval_overall_precision": 0.9144254278728606,
"eval_overall_recall": 0.9326683291770573,
"eval_runtime": 0.2432,
"eval_samples_per_second": 698.874,
"eval_steps_per_second": 12.333,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.10606043040752411,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0179,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.911917098445596,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.88,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.920245398773006,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.059012968093156815,
"eval_overall_accuracy": 0.9871056241426612,
"eval_overall_f1": 0.9378109452736318,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.047,
"eval_steps_per_second": 12.354,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.39132779836654663,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0173,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9072164948453608,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8712871287128713,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.911854103343465,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06428411602973938,
"eval_overall_accuracy": 0.9862825788751715,
"eval_overall_f1": 0.9305210918114145,
"eval_overall_precision": 0.9259259259259259,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.165,
"eval_steps_per_second": 12.356,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.08335191756486893,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.0199,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9107142857142857,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06521153450012207,
"eval_overall_accuracy": 0.9854595336076818,
"eval_overall_f1": 0.9320148331273177,
"eval_overall_precision": 0.9240196078431373,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.527,
"eval_steps_per_second": 12.345,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 0.518538236618042,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0183,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9112426035502958,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06252401322126389,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9379652605459058,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.167,
"eval_steps_per_second": 12.321,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.44658711552619934,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0176,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9166666666666667,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8888888888888888,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05770767852663994,
"eval_overall_accuracy": 0.988477366255144,
"eval_overall_f1": 0.9356435643564357,
"eval_overall_precision": 0.9287469287469288,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.352,
"eval_steps_per_second": 12.394,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.25108611583709717,
"learning_rate": 2.5e-05,
"loss": 0.0176,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9326424870466321,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.967741935483871,
"eval_ORGANIZATION_f1": 0.911854103343465,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.9716312056737589,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9785714285714285,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06235959753394127,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9378109452736318,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2453,
"eval_samples_per_second": 693.012,
"eval_steps_per_second": 12.23,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.09793492406606674,
"learning_rate": 2.45e-05,
"loss": 0.017,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9134328358208955,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9053254437869822,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9616724738675958,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9517241379310345,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0605827234685421,
"eval_overall_accuracy": 0.9871056241426612,
"eval_overall_f1": 0.9321824907521579,
"eval_overall_precision": 0.9219512195121952,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.243,
"eval_samples_per_second": 699.456,
"eval_steps_per_second": 12.343,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.5036334991455078,
"learning_rate": 2.4e-05,
"loss": 0.0174,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9253731343283581,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06373578310012817,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9416149068322982,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.124,
"eval_steps_per_second": 12.355,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 1.246224045753479,
"learning_rate": 2.35e-05,
"loss": 0.0172,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9197860962566845,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9148936170212766,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9074626865671641,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8994082840236687,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9614035087719298,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.958041958041958,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06175196170806885,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9293680297397771,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.211,
"eval_steps_per_second": 12.392,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.04277476295828819,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0162,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9368421052631579,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9175257731958762,
"eval_LOCATION_recall": 0.956989247311828,
"eval_ORGANIZATION_f1": 0.9074626865671641,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.8994082840236687,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.05818229168653488,
"eval_overall_accuracy": 0.9871056241426612,
"eval_overall_f1": 0.9344870210135972,
"eval_overall_precision": 0.9264705882352942,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.91,
"eval_steps_per_second": 12.351,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.3680441975593567,
"learning_rate": 2.25e-05,
"loss": 0.0158,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9214659685863874,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9146341463414634,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9259259259259259,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06128155067563057,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9353233830845771,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2429,
"eval_samples_per_second": 700.01,
"eval_steps_per_second": 12.353,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.6982637643814087,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0154,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9214659685863874,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8979591836734694,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9101796407185628,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9047619047619048,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.061201851814985275,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9331683168316831,
"eval_overall_precision": 0.9262899262899262,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2431,
"eval_samples_per_second": 699.199,
"eval_steps_per_second": 12.339,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.46794214844703674,
"learning_rate": 2.15e-05,
"loss": 0.0167,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9025641025641027,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8627450980392157,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.911854103343465,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9202453987730062,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.05949314311146736,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9293680297397771,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.495,
"eval_steps_per_second": 12.362,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.699009895324707,
"learning_rate": 2.1e-05,
"loss": 0.0161,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.8979591836734693,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8543689320388349,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9197530864197531,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9430379746835443,
"eval_ORGANIZATION_recall": 0.8975903614457831,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0642397403717041,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9328358208955224,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2422,
"eval_samples_per_second": 701.957,
"eval_steps_per_second": 12.387,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 0.3389071226119995,
"learning_rate": 2.05e-05,
"loss": 0.0148,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0570293590426445,
"eval_overall_accuracy": 0.9887517146776406,
"eval_overall_f1": 0.9416149068322982,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.778,
"eval_steps_per_second": 12.331,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.07280365377664566,
"learning_rate": 2e-05,
"loss": 0.0143,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9312169312169313,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.05907455459237099,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9429280397022332,
"eval_overall_precision": 0.9382716049382716,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.2433,
"eval_samples_per_second": 698.597,
"eval_steps_per_second": 12.328,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 1.0050455331802368,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0123,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.8936170212765957,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8842105263157894,
"eval_LOCATION_recall": 0.9032258064516129,
"eval_ORGANIZATION_f1": 0.9156626506024096,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9614035087719298,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.958041958041958,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06302603334188461,
"eval_overall_accuracy": 0.9860082304526749,
"eval_overall_f1": 0.9267080745341615,
"eval_overall_precision": 0.9232673267326733,
"eval_overall_recall": 0.9301745635910225,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.703,
"eval_steps_per_second": 12.312,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 0.4894563853740692,
"learning_rate": 1.9e-05,
"loss": 0.013,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06771185249090195,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9353233830845771,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.96,
"eval_steps_per_second": 12.352,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.48578622937202454,
"learning_rate": 1.85e-05,
"loss": 0.0136,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9134328358208955,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9053254437869822,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9614035087719298,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.958041958041958,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06076972559094429,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9343246592317225,
"eval_overall_precision": 0.9285714285714286,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2432,
"eval_samples_per_second": 699.101,
"eval_steps_per_second": 12.337,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 1.1228235960006714,
"learning_rate": 1.8e-05,
"loss": 0.0123,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9216867469879518,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06617654860019684,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9391304347826087,
"eval_overall_precision": 0.9356435643564357,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.132,
"eval_steps_per_second": 12.391,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.5067967772483826,
"learning_rate": 1.75e-05,
"loss": 0.0138,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9123867069486404,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06384352594614029,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9293680297397771,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2448,
"eval_samples_per_second": 694.309,
"eval_steps_per_second": 12.253,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.5749635100364685,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0126,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9263157894736843,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9072164948453608,
"eval_LOCATION_recall": 0.946236559139785,
"eval_ORGANIZATION_f1": 0.9123867069486404,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06462161988019943,
"eval_overall_accuracy": 0.9871056241426612,
"eval_overall_f1": 0.9353233830845771,
"eval_overall_precision": 0.9330024813895782,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.244,
"eval_samples_per_second": 696.842,
"eval_steps_per_second": 12.297,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.6921520233154297,
"learning_rate": 1.65e-05,
"loss": 0.0132,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9109947643979057,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8877551020408163,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9063444108761329,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9090909090909091,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.965034965034965,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9583333333333334,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06951480358839035,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9282178217821783,
"eval_overall_precision": 0.9213759213759214,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2427,
"eval_samples_per_second": 700.573,
"eval_steps_per_second": 12.363,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.5449104905128479,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0117,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06366503238677979,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9378109452736318,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2415,
"eval_samples_per_second": 703.968,
"eval_steps_per_second": 12.423,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.6479567289352417,
"learning_rate": 1.55e-05,
"loss": 0.0132,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06647858023643494,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2425,
"eval_samples_per_second": 701.153,
"eval_steps_per_second": 12.373,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.9923555850982666,
"learning_rate": 1.5e-05,
"loss": 0.012,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9197860962566845,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9148936170212766,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9253731343283581,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06690575182437897,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9392812887236679,
"eval_overall_precision": 0.9334975369458128,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.178,
"eval_steps_per_second": 12.321,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.5946698188781738,
"learning_rate": 1.45e-05,
"loss": 0.0126,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9309309309309309,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9681978798586572,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9716312056737588,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06453956663608551,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9416149068322982,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.244,
"eval_samples_per_second": 696.596,
"eval_steps_per_second": 12.293,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.3587588965892792,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0122,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.9100529100529101,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9300911854103343,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06485585868358612,
"eval_overall_accuracy": 0.9871056241426612,
"eval_overall_f1": 0.941469489414695,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.694,
"eval_steps_per_second": 12.383,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 2.4061574935913086,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0124,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9100529100529101,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9305135951661632,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06097925454378128,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9416149068322982,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.609,
"eval_steps_per_second": 12.399,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.18058377504348755,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0112,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9052631578947367,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8865979381443299,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9179331306990882,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9263803680981595,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06555599719285965,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9339975093399752,
"eval_overall_precision": 0.9328358208955224,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.2429,
"eval_samples_per_second": 699.983,
"eval_steps_per_second": 12.353,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 0.5010203123092651,
"learning_rate": 1.25e-05,
"loss": 0.011,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9052631578947367,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8865979381443299,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9337349397590361,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9337349397590361,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06436942517757416,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9417596034696407,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9476309226932669,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.55,
"eval_steps_per_second": 12.31,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.2402101457118988,
"learning_rate": 1.2e-05,
"loss": 0.0095,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.9100529100529101,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06596006453037262,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9404466501240694,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.244,
"eval_samples_per_second": 696.651,
"eval_steps_per_second": 12.294,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.03723614662885666,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0103,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.90625,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8787878787878788,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9174311926605505,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9316770186335404,
"eval_ORGANIZATION_recall": 0.9036144578313253,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06691861152648926,
"eval_overall_accuracy": 0.9865569272976681,
"eval_overall_f1": 0.9341614906832298,
"eval_overall_precision": 0.9306930693069307,
"eval_overall_recall": 0.9376558603491272,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.704,
"eval_steps_per_second": 12.383,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.0136006074026227,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.0102,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9157894736842105,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9272727272727274,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06402508169412613,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2437,
"eval_samples_per_second": 697.679,
"eval_steps_per_second": 12.312,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.029908180236816406,
"learning_rate": 1.05e-05,
"loss": 0.0105,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9354838709677419,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9354838709677419,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9300911854103343,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06250619888305664,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9463171036204744,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.296,
"eval_steps_per_second": 12.305,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.41899558901786804,
"learning_rate": 1e-05,
"loss": 0.0099,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9157894736842105,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8969072164948454,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9123867069486404,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9151515151515152,
"eval_ORGANIZATION_recall": 0.9096385542168675,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06478453427553177,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9343246592317225,
"eval_overall_precision": 0.9285714285714286,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2435,
"eval_samples_per_second": 698.072,
"eval_steps_per_second": 12.319,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.549152135848999,
"learning_rate": 9.5e-06,
"loss": 0.009,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.9100529100529101,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9156626506024096,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06385954469442368,
"eval_overall_accuracy": 0.9868312757201646,
"eval_overall_f1": 0.9343246592317225,
"eval_overall_precision": 0.9285714285714286,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2423,
"eval_samples_per_second": 701.601,
"eval_steps_per_second": 12.381,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.7205570340156555,
"learning_rate": 9e-06,
"loss": 0.01,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.9405405405405404,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9456521739130435,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9216867469879518,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.972027972027972,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9652777777777778,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06512189656496048,
"eval_overall_accuracy": 0.9887517146776406,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.286,
"eval_steps_per_second": 12.358,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.22340303659439087,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0093,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.9206349206349206,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.90625,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9212121212121213,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06695973873138428,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2439,
"eval_samples_per_second": 697.033,
"eval_steps_per_second": 12.301,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.21084712445735931,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0094,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.918429003021148,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9212121212121213,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06592698395252228,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.940149625935162,
"eval_overall_precision": 0.940149625935162,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2434,
"eval_samples_per_second": 698.361,
"eval_steps_per_second": 12.324,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.8988425135612488,
"learning_rate": 7.5e-06,
"loss": 0.0118,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9100529100529101,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.8958333333333334,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9212121212121213,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.926829268292683,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.9614035087719298,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.958041958041958,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06450724601745605,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9328358208955224,
"eval_overall_precision": 0.9305210918114144,
"eval_overall_recall": 0.9351620947630923,
"eval_runtime": 0.242,
"eval_samples_per_second": 702.343,
"eval_steps_per_second": 12.394,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.23599927127361298,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0091,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9297297297297297,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9347826086956522,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06411174684762955,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9413233458177278,
"eval_overall_precision": 0.9425,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.274,
"eval_steps_per_second": 12.411,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.1380176842212677,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0094,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9247311827956989,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9247311827956989,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9221556886227544,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.9647887323943662,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.9647887323943662,
"eval_PERSON_recall": 0.9647887323943662,
"eval_loss": 0.06503292173147202,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9378109452736318,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.809,
"eval_steps_per_second": 12.403,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.6239321827888489,
"learning_rate": 6e-06,
"loss": 0.0093,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9197860962566845,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9148936170212766,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9305135951661632,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9333333333333333,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06462183594703674,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.941469489414695,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2426,
"eval_samples_per_second": 700.841,
"eval_steps_per_second": 12.368,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.22308340668678284,
"learning_rate": 5.500000000000001e-06,
"loss": 0.009,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.9247311827956989,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9247311827956989,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.968421052631579,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.965034965034965,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0633547380566597,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.34,
"eval_steps_per_second": 12.377,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.3860442042350769,
"learning_rate": 5e-06,
"loss": 0.0081,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9354838709677419,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9354838709677419,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9216867469879518,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.9754385964912281,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.972027972027972,
"eval_PERSON_recall": 0.9788732394366197,
"eval_loss": 0.06675305962562561,
"eval_overall_accuracy": 0.988477366255144,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2421,
"eval_samples_per_second": 702.327,
"eval_steps_per_second": 12.394,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.10230008512735367,
"learning_rate": 4.5e-06,
"loss": 0.0089,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9247311827956989,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9247311827956989,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9309309309309309,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06702690571546555,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.253,
"eval_steps_per_second": 12.357,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 1.1152575016021729,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0085,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.925531914893617,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9157894736842105,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9156626506024096,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9156626506024096,
"eval_ORGANIZATION_recall": 0.9156626506024096,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06895388662815094,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.9378109452736318,
"eval_overall_precision": 0.9354838709677419,
"eval_overall_recall": 0.940149625935162,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.097,
"eval_steps_per_second": 12.355,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.1009005755186081,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0099,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9354838709677419,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9354838709677419,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.0674271360039711,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9451371571072319,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2428,
"eval_samples_per_second": 700.115,
"eval_steps_per_second": 12.355,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.059238094836473465,
"learning_rate": 3e-06,
"loss": 0.0095,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9405405405405404,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9456521739130435,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.927710843373494,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06816842406988144,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9463171036204744,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2452,
"eval_samples_per_second": 693.35,
"eval_steps_per_second": 12.236,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.2613770365715027,
"learning_rate": 2.5e-06,
"loss": 0.0086,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9405405405405404,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9456521739130435,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.924924924924925,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9221556886227545,
"eval_ORGANIZATION_recall": 0.927710843373494,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06779375672340393,
"eval_overall_accuracy": 0.9882030178326474,
"eval_overall_f1": 0.9451371571072319,
"eval_overall_precision": 0.9451371571072319,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2418,
"eval_samples_per_second": 703.005,
"eval_steps_per_second": 12.406,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.4493662118911743,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0079,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9247311827956989,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.9247311827956989,
"eval_LOCATION_recall": 0.9247311827956989,
"eval_ORGANIZATION_f1": 0.9309309309309309,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9337349397590361,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06615590304136276,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.9439601494396015,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9451371571072319,
"eval_runtime": 0.2417,
"eval_samples_per_second": 703.399,
"eval_steps_per_second": 12.413,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.13826021552085876,
"learning_rate": 1.5e-06,
"loss": 0.0084,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9216867469879518,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06691529601812363,
"eval_overall_accuracy": 0.9879286694101509,
"eval_overall_f1": 0.941469489414695,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.307,
"eval_steps_per_second": 12.376,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.26197510957717896,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0085,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9216867469879518,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9216867469879518,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06786871701478958,
"eval_overall_accuracy": 0.9873799725651577,
"eval_overall_f1": 0.941469489414695,
"eval_overall_precision": 0.9402985074626866,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2419,
"eval_samples_per_second": 702.859,
"eval_steps_per_second": 12.403,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.20004457235336304,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0071,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06792567670345306,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2438,
"eval_samples_per_second": 697.166,
"eval_steps_per_second": 12.303,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.022885635495185852,
"learning_rate": 0.0,
"loss": 0.0079,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9304812834224598,
"eval_LOCATION_number": 93,
"eval_LOCATION_precision": 0.925531914893617,
"eval_LOCATION_recall": 0.9354838709677419,
"eval_ORGANIZATION_f1": 0.9189189189189191,
"eval_ORGANIZATION_number": 166,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.9216867469879518,
"eval_PERSON_f1": 0.971830985915493,
"eval_PERSON_number": 142,
"eval_PERSON_precision": 0.971830985915493,
"eval_PERSON_recall": 0.971830985915493,
"eval_loss": 0.06780911237001419,
"eval_overall_accuracy": 0.9876543209876543,
"eval_overall_f1": 0.9402985074626866,
"eval_overall_precision": 0.9379652605459057,
"eval_overall_recall": 0.942643391521197,
"eval_runtime": 0.2424,
"eval_samples_per_second": 701.311,
"eval_steps_per_second": 12.376,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4208466347875278.0,
"train_loss": 0.038929777735223374,
"train_runtime": 473.1614,
"train_samples_per_second": 323.568,
"train_steps_per_second": 20.289
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4208466347875278.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}