model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/roberta_large_concat/best_model",
+  "_name_or_path": "roberta-large",
   "adapters": {
     "adapters": {},
     "config_map": {},

eval/metric.json

@@ -1 +1 @@
-{"2020.dev": {"micro/f1": 0.6569543705332601, "micro/f1_ci": {"90": [0.6347708061707447, 0.675787762538431], "95": [0.6315458913405132, 0.6789961088599261]}, "micro/recall": 0.6243469174503657, "micro/precision": 0.6931554524361949, "macro/f1": 0.6071703884347733, "macro/f1_ci": {"90": [0.5842888341668635, 0.6272437871418639], "95": [0.5798781678355553, 0.6309167018785864]}, "macro/recall": 0.5768996197534351, "macro/precision": 0.6505290877604671, "per_entity_metric": {"corporation": {"f1": 0.5219941348973607, "f1_ci": {"90": [0.4574780058651027, 0.5763688760806917], "95": [0.44520339124624125, 0.5885562475671468]}, "precision": 0.644927536231884, "recall": 0.43842364532019706}, "creative_work": {"f1": 0.5555555555555556, "f1_ci": {"90": [0.4925531612328286, 0.6081887366818874], "95": [0.477124183006536, 0.6200120481927712]}, "precision": 0.6578947368421053, "recall": 0.4807692307692308}, "event": {"f1": 0.3737166324435318, "f1_ci": {"90": [0.32148941298339, 0.4247155049786628], "95": [0.31484302510465717, 0.4322250767382891]}, "precision": 0.3939393939393939, "recall": 0.35546875}, "group": {"f1": 0.5807770961145193, "f1_ci": {"90": [0.5275139764908258, 0.6275909121462661], "95": [0.5189204545454545, 0.6361928193310445]}, "precision": 0.5419847328244275, "recall": 0.6255506607929515}, "location": {"f1": 0.6666666666666666, "f1_ci": {"90": [0.6095185331750428, 0.7147472409437143], "95": [0.5951683238877389, 0.7281801905492677]}, "precision": 0.6542553191489362, "recall": 0.6795580110497238}, "person": {"f1": 0.8665511265164645, "f1_ci": {"90": [0.8438121549252551, 0.8865095226489329], "95": [0.8386447010869564, 0.8910758099658961]}, "precision": 0.8992805755395683, "recall": 0.8361204013377926}, "product": {"f1": 0.6849315068493151, "f1_ci": {"90": [0.6361345844206319, 0.7276693316215375], "95": [0.6277119983854149, 0.7336193346190936]}, "precision": 0.7614213197969543, "recall": 0.6224066390041494}}}, "2021.test": {"micro/f1": 0.6574934067194129, "micro/f1_ci": {"90": [0.6488384906771661, 0.6668708832165559], "95": [0.6465245785916518, 0.6685455948975375]}, "micro/recall": 0.6630434782608695, "micro/precision": 0.6520354787355015, "macro/f1": 0.6118476204727268, "macro/f1_ci": {"90": [0.6017404898343343, 0.6217032067276532], "95": [0.5998330900671207, 0.6231511559289998]}, "macro/recall": 0.6175539552781218, "macro/precision": 0.6072477857570534, "per_entity_metric": {"corporation": {"f1": 0.541899441340782, "f1_ci": {"90": [0.5186795598247989, 0.5685856621094023], "95": [0.5126138225832753, 0.5743503513898618]}, "precision": 0.5449438202247191, "recall": 0.5388888888888889}, "creative_work": {"f1": 0.46601941747572817, "f1_ci": {"90": [0.4353626239768139, 0.4989775051124744], "95": [0.43055507794589637, 0.5059671468032207]}, "precision": 0.47257383966244726, "recall": 0.45964432284541723}, "event": {"f1": 0.49394221808014904, "f1_ci": {"90": [0.46986206833907485, 0.5162773107105282], "95": [0.4663047835964417, 0.5204910201076981]}, "precision": 0.5062082139446036, "recall": 0.4822565969062784}, "group": {"f1": 0.6076659395450296, "f1_ci": {"90": [0.5869813402758498, 0.6292822463184621], "95": [0.5833058401946332, 0.6339008885966244]}, "precision": 0.576581904198699, "recall": 0.642292490118577}, "location": {"f1": 0.6697674418604651, "f1_ci": {"90": [0.6431739079049713, 0.6956575951425783], "95": [0.638513775592407, 0.6994724542049008]}, "precision": 0.6387832699619772, "recall": 0.7039106145251397}, "person": {"f1": 0.8321060382916053, "f1_ci": {"90": [0.8215742088885891, 0.8431088930663221], "95": [0.8197897485813659, 0.844858913782981]}, "precision": 0.8308823529411765, "recall": 0.8333333333333334}, "product": {"f1": 0.6715328467153284, "f1_ci": {"90": [0.649823578485181, 0.6921889493709199], "95": [0.6449209966416612, 0.6959884403753066]}, "precision": 0.6807610993657506, "recall": 0.6625514403292181}}}, "2020.test": {"micro/f1": 0.6490030046435399, "micro/f1_ci": {"90": [0.6289418548289524, 0.668141458100033], "95": [0.6249252774003541, 0.6725029471927343]}, "micro/recall": 0.6165023352361183, "micro/precision": 0.6851211072664359, "macro/f1": 0.6137144801993001, "macro/f1_ci": {"90": [0.5921297090566222, 0.6343935788610027], "95": [0.5882584824882211, 0.638865227814623]}, "macro/recall": 0.5808559297761207, "macro/precision": 0.6514440514516731, "per_entity_metric": {"corporation": {"f1": 0.5722543352601156, "f1_ci": {"90": [0.5085396825396825, 0.628099173553719], "95": [0.4955725476566051, 0.6370768029046094]}, "precision": 0.6387096774193548, "recall": 0.518324607329843}, "creative_work": {"f1": 0.5176470588235295, "f1_ci": {"90": [0.4589757904887581, 0.5744010277473017], "95": [0.4495016858106177, 0.585654161001996]}, "precision": 0.546583850931677, "recall": 0.49162011173184356}, "event": {"f1": 0.4701348747591523, "f1_ci": {"90": [0.41884503039393695, 0.5178236397748592], "95": [0.41117694923741366, 0.5247983740763956]}, "precision": 0.48031496062992124, "recall": 0.46037735849056605}, "group": {"f1": 0.5561312607944734, "f1_ci": {"90": [0.5053600521342457, 0.605074580444502], "95": [0.4974327603118063, 0.6153903903903905]}, "precision": 0.6007462686567164, "recall": 0.5176848874598071}, "location": {"f1": 0.6729559748427673, "f1_ci": {"90": [0.6073081783715472, 0.7337578575170246], "95": [0.5973079234698988, 0.7469276094276096]}, "precision": 0.6993464052287581, "recall": 0.6484848484848484}, "person": {"f1": 0.817391304347826, "f1_ci": {"90": [0.7891867433043904, 0.8432835843761107], "95": [0.785072596776479, 0.8466064618376089]}, "precision": 0.8483754512635379, "recall": 0.7885906040268457}, "product": {"f1": 0.6894865525672372, "f1_ci": {"90": [0.6385614324393587, 0.7354514422256357], "95": [0.6277188528286759, 0.7440663925875929]}, "precision": 0.746031746031746, "recall": 0.6409090909090909}}}, "2021.test (span detection)": {"micro/f1": 0.7902069835445216, "micro/f1_ci": {}, "micro/recall": 0.7969237885972014, "micro/precision": 0.7836024562201501, "macro/f1": 0.7902069835445216, "macro/f1_ci": {}, "macro/recall": 0.7969237885972014, "macro/precision": 0.7836024562201501}, "2020.test (span detection)": {"micro/f1": 0.7557377049180328, "micro/f1_ci": {}, "micro/recall": 0.7176959003632589, "micro/precision": 0.7980380842469705, "macro/f1": 0.7557377049180328, "macro/f1_ci": {}, "macro/recall": 0.7176959003632589, "macro/precision": 0.7980380842469705}, "2020.dev (span detection)": {"micro/f1": 0.7680043980208907, "micro/f1_ci": {}, "micro/recall": 0.7298850574712644, "micro/precision": 0.8103248259860789, "macro/f1": 0.7680043980208907, "macro/f1_ci": {}, "macro/recall": 0.7298850574712644, "macro/precision": 0.8103248259860789}}
+{"2021.dev": {"micro/f1": 0.6533466533466533, "micro/f1_ci": {}, "micro/recall": 0.654, "micro/precision": 0.6526946107784432, "macro/f1": 0.6139317233528648, "macro/f1_ci": {}, "macro/recall": 0.6070190930048767, "macro/precision": 0.6237479137205354, "per_entity_metric": {"corporation": {"f1": 0.5631067961165048, "f1_ci": {}, "precision": 0.5576923076923077, "recall": 0.5686274509803921}, "creative_work": {"f1": 0.47297297297297297, "f1_ci": {}, "precision": 0.47297297297297297, "recall": 0.47297297297297297}, "event": {"f1": 0.4505928853754941, "f1_ci": {}, "precision": 0.4672131147540984, "recall": 0.4351145038167939}, "group": {"f1": 0.6345733041575492, "f1_ci": {}, "precision": 0.6304347826086957, "recall": 0.6387665198237885}, "location": {"f1": 0.7076923076923076, "f1_ci": {}, "precision": 0.7931034482758621, "recall": 0.6388888888888888}, "person": {"f1": 0.8231292517006802, "f1_ci": {}, "precision": 0.7934426229508197, "recall": 0.8551236749116607}, "product": {"f1": 0.6454545454545454, "f1_ci": {}, "precision": 0.6513761467889908, "recall": 0.6396396396396397}}}, "2021.test": {"micro/f1": 0.6574551220340903, "micro/f1_ci": {"90": [0.6484148010152769, 0.6672289519134409], "95": [0.6470100684797441, 0.6689850350992637]}, "micro/recall": 0.6712534690101758, "micro/precision": 0.644212629008989, "macro/f1": 0.6124665667529737, "macro/f1_ci": {"90": [0.6027797907638927, 0.6224386923123064], "95": [0.600643831363655, 0.6236643933399094]}, "macro/recall": 0.625251837701222, "macro/precision": 0.6005167968535563, "per_entity_metric": {"corporation": {"f1": 0.5392156862745098, "f1_ci": {"90": [0.5150666283343305, 0.5627638588284978], "95": [0.5107747807572307, 0.5685865874978943]}, "precision": 0.5288461538461539, "recall": 0.55}, "creative_work": {"f1": 0.4760582928521859, "f1_ci": {"90": [0.44542457349745634, 0.508050611843474], "95": [0.43965273913172126, 0.5137357875658368]}, "precision": 0.4830985915492958, "recall": 0.4692202462380301}, "event": {"f1": 0.4673321234119782, "f1_ci": {"90": [0.4453263502657273, 0.4898926859987146], "95": [0.4407011814810304, 0.4935304881902431]}, "precision": 0.4660633484162896, "recall": 0.46860782529572337}, "group": {"f1": 0.6139798488664987, "f1_ci": {"90": [0.5937377152453256, 0.6348052094376245], "95": [0.5916896908608198, 0.6386072364652792]}, "precision": 0.5880579010856454, "recall": 0.642292490118577}, "location": {"f1": 0.6707399864222675, "f1_ci": {"90": [0.6421888503799826, 0.6973484858175715], "95": [0.6384158152719541, 0.702529512070608]}, "precision": 0.6525759577278731, "recall": 0.6899441340782123}, "person": {"f1": 0.8293212669683258, "f1_ci": {"90": [0.8181446413482045, 0.8403938359511686], "95": [0.8159141098754302, 0.8428604160939993]}, "precision": 0.8144329896907216, "recall": 0.8447640117994101}, "product": {"f1": 0.6906187624750498, "f1_ci": {"90": [0.6702170960229447, 0.7112006663611212], "95": [0.6659795602550325, 0.714153086982773]}, "precision": 0.6705426356589147, "recall": 0.7119341563786008}}}, "2020.test": {"micro/f1": 0.6628787878787878, "micro/f1_ci": {"90": [0.6433422832233964, 0.6809899075848771], "95": [0.6396017768782147, 0.6838039347472534]}, "micro/recall": 0.6357031655422937, "micro/precision": 0.6924816280384398, "macro/f1": 0.6297223287745568, "macro/f1_ci": {"90": [0.6077306460764652, 0.649687103374554], "95": [0.6035631307519294, 0.6525413558422907]}, "macro/recall": 0.601311568050436, "macro/precision": 0.6618492079232416, "per_entity_metric": {"corporation": {"f1": 0.6183844011142062, "f1_ci": {"90": [0.5604604257738921, 0.6691009721496806], "95": [0.5487777897690481, 0.6787612489773658]}, "precision": 0.6607142857142857, "recall": 0.581151832460733}, "creative_work": {"f1": 0.5159420289855072, "f1_ci": {"90": [0.4561346362649294, 0.5690866992079243], "95": [0.44507064868336543, 0.5785442676279234]}, "precision": 0.536144578313253, "recall": 0.4972067039106145}, "event": {"f1": 0.5028790786948176, "f1_ci": {"90": [0.4574887305511124, 0.5513362750160383], "95": [0.44581993761996164, 0.5625028357531761]}, "precision": 0.51171875, "recall": 0.49433962264150944}, "group": {"f1": 0.5598591549295774, "f1_ci": {"90": [0.5130891913483878, 0.6074147053457399], "95": [0.5018050541516246, 0.6181973581973583]}, "precision": 0.6186770428015564, "recall": 0.5112540192926045}, "location": {"f1": 0.6923076923076923, "f1_ci": {"90": [0.6291361251400163, 0.75], "95": [0.6172724125995154, 0.7622443181818181]}, "precision": 0.7346938775510204, "recall": 0.6545454545454545}, "person": {"f1": 0.8201193520886614, "f1_ci": {"90": [0.7918366950327573, 0.8450477632944151], "95": [0.7872476092967537, 0.8496363016720296]}, "precision": 0.8336221837088388, "recall": 0.8070469798657718}, "product": {"f1": 0.6985645933014354, "f1_ci": {"90": [0.6469248291571754, 0.744086649786838], "95": [0.6368046132971505, 0.7505999077065068]}, "precision": 0.7373737373737373, "recall": 0.6636363636363637}}}, "2021.test (span detection)": {"micro/f1": 0.7881979839166384, "micro/f1_ci": {}, "micro/recall": 0.804787787672025, "micro/precision": 0.7722783264898457, "macro/f1": 0.7881979839166384, "macro/f1_ci": {}, "macro/recall": 0.804787787672025, "macro/precision": 0.7722783264898457}, "2020.test (span detection)": {"micro/f1": 0.7642760487144791, "micro/f1_ci": {}, "micro/recall": 0.7327451997924235, "micro/precision": 0.7986425339366516, "macro/f1": 0.7642760487144791, "macro/f1_ci": {}, "macro/recall": 0.7327451997924235, "macro/precision": 0.7986425339366516}}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cner_output/model/baseline_2021/roberta_large_concat/best_model", "tokenizer_class": "RobertaTokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2020_2021.train", "model": "roberta-large", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-05, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.15, "max_grad_norm": 1}