model update

config.json

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

eval/metric.json

@@ -1 +1 @@
-{"2020.dev": {"micro/f1": 0.6243930305626962, "micro/f1_ci": {"90": [0.6003428575393531, 0.6453894322099486], "95": [0.5953974521674013, 0.649533445350206]}, "micro/recall": 0.571055381400209, "micro/precision": 0.6887208569628229, "macro/f1": 0.5644244568345999, "macro/f1_ci": {"90": [0.5398432773509213, 0.5863131877116426], "95": [0.5355602963026352, 0.590281175701375]}, "macro/recall": 0.516573701258573, "macro/precision": 0.6279840088923073, "per_entity_metric": {"corporation": {"f1": 0.46560846560846564, "f1_ci": {"90": [0.4078055027184088, 0.5181680463471217], "95": [0.39888945610966525, 0.5289821475979877]}, "precision": 0.5028571428571429, "recall": 0.43349753694581283}, "creative_work": {"f1": 0.5055555555555555, "f1_ci": {"90": [0.4397549985464647, 0.5664739884393063], "95": [0.4285613682092556, 0.5745959944751382]}, "precision": 0.5986842105263158, "recall": 0.4375}, "event": {"f1": 0.3515439429928741, "f1_ci": {"90": [0.29475856843152887, 0.40566721356302976], "95": [0.28288490853658527, 0.417910447761194]}, "precision": 0.4484848484848485, "recall": 0.2890625}, "group": {"f1": 0.5294117647058824, "f1_ci": {"90": [0.4735442681815746, 0.5790833211914326], "95": [0.46191616941616936, 0.5898281596452329]}, "precision": 0.5441860465116279, "recall": 0.5154185022026432}, "location": {"f1": 0.6069364161849711, "f1_ci": {"90": [0.542678118027237, 0.657537969029184], "95": [0.5302579154014273, 0.6702717552717553]}, "precision": 0.6363636363636364, "recall": 0.580110497237569}, "person": {"f1": 0.851138353765324, "f1_ci": {"90": [0.8275832771804411, 0.8703597631365321], "95": [0.8219812125014074, 0.8751063548806451]}, "precision": 0.8933823529411765, "recall": 0.8127090301003345}, "product": {"f1": 0.6407766990291263, "f1_ci": {"90": [0.5885140090949098, 0.6855971704321123], "95": [0.5770954341592529, 0.6937983309805491]}, "precision": 0.7719298245614035, "recall": 0.5477178423236515}}}, "2021.test": {"micro/f1": 0.6511765401442592, "micro/f1_ci": {"90": [0.6421787214767234, 0.6610407027421309], "95": [0.6401339666471219, 0.662248539708265]}, "micro/recall": 0.6367946345975948, "micro/precision": 0.6662230825066537, "macro/f1": 0.6002870922146754, "macro/f1_ci": {"90": [0.5907680043523333, 0.6108613404146909], "95": [0.5890321402925847, 0.6127525074911567]}, "macro/recall": 0.5882008286621916, "macro/precision": 0.6161696747986873, "per_entity_metric": {"corporation": {"f1": 0.5333333333333332, "f1_ci": {"90": [0.5079650158539651, 0.5584434571276677], "95": [0.5043278456019357, 0.5629363877706922]}, "precision": 0.5054726368159204, "recall": 0.5644444444444444}, "creative_work": {"f1": 0.44924406047516197, "f1_ci": {"90": [0.41691220220935865, 0.48489171595717995], "95": [0.4099140631777827, 0.49065968482937494]}, "precision": 0.47416413373860183, "recall": 0.426812585499316}, "event": {"f1": 0.47368421052631576, "f1_ci": {"90": [0.4488904907422461, 0.49659109071953333], "95": [0.4445651881405906, 0.5019891905311733]}, "precision": 0.5470798569725864, "recall": 0.4176524112829845}, "group": {"f1": 0.6144138160079707, "f1_ci": {"90": [0.5948790506165442, 0.6361976777894752], "95": [0.5917984711592787, 0.6399648449441256]}, "precision": 0.6195579370395178, "recall": 0.6093544137022397}, "location": {"f1": 0.6532871972318338, "f1_ci": {"90": [0.6250765047583734, 0.6819782420410228], "95": [0.6196532903157452, 0.6868632596731649]}, "precision": 0.6474622770919067, "recall": 0.659217877094972}, "person": {"f1": 0.8304485389912526, "f1_ci": {"90": [0.820053685826094, 0.8415785120415923], "95": [0.8178342880670223, 0.8435423355038384]}, "precision": 0.8384066140548666, "recall": 0.8226401179941003}, "product": {"f1": 0.6475984889368591, "f1_ci": {"90": [0.625, 0.6689421739933686], "95": [0.6202192209014791, 0.6733410201693398]}, "precision": 0.681044267877412, "recall": 0.6172839506172839}}}, "2020.test": {"micro/f1": 0.6355717898286035, "micro/f1_ci": {"90": [0.6159904584429052, 0.6533795212920971], "95": [0.6125240443922205, 0.658576779844267]}, "micro/recall": 0.5869226777374157, "micro/precision": 0.6930147058823529, "macro/f1": 0.5938255352101665, "macro/f1_ci": {"90": [0.5718237818604409, 0.6133399430835145], "95": [0.5683226633789384, 0.6168777983531797]}, "macro/recall": 0.5492809368031558, "macro/precision": 0.6491448118409477, "per_entity_metric": {"corporation": {"f1": 0.556149732620321, "f1_ci": {"90": [0.4927711135933175, 0.6108511220580186], "95": [0.4804125877498157, 0.619513520678685]}, "precision": 0.5683060109289617, "recall": 0.5445026178010471}, "creative_work": {"f1": 0.5031847133757962, "f1_ci": {"90": [0.44376899696048633, 0.5555555555555556], "95": [0.4347826086956522, 0.5642880164528211]}, "precision": 0.5851851851851851, "recall": 0.441340782122905}, "event": {"f1": 0.42888402625820565, "f1_ci": {"90": [0.37384046726151987, 0.4838774193548387], "95": [0.36395077262693154, 0.4927314410796165]}, "precision": 0.5104166666666666, "recall": 0.36981132075471695}, "group": {"f1": 0.5683836589698046, "f1_ci": {"90": [0.5188878309009783, 0.622127323254213], "95": [0.5088024681443408, 0.633282428782725]}, "precision": 0.6349206349206349, "recall": 0.5144694533762058}, "location": {"f1": 0.6603174603174603, "f1_ci": {"90": [0.5999694189602446, 0.7151534330648255], "95": [0.588224752266498, 0.7273007856341192]}, "precision": 0.6933333333333334, "recall": 0.6303030303030303}, "person": {"f1": 0.8098591549295776, "f1_ci": {"90": [0.7812432939914162, 0.835548541897379], "95": [0.7752081956478242, 0.842392376976191]}, "precision": 0.8518518518518519, "recall": 0.7718120805369127}, "product": {"f1": 0.63, "f1_ci": {"90": [0.5765218156228009, 0.6791613273827934], "95": [0.5671641791044777, 0.6888441175628881]}, "precision": 0.7, "recall": 0.5727272727272728}}}, "2021.test (span detection)": {"micro/f1": 0.7804647312718028, "micro/f1_ci": {}, "micro/recall": 0.7632704984387649, "micro/precision": 0.7984514880232276, "macro/f1": 0.7804647312718028, "macro/f1_ci": {}, "macro/recall": 0.7632704984387649, "macro/precision": 0.7984514880232276}, "2020.test (span detection)": {"micro/f1": 0.7470489038785835, "micro/f1_ci": {}, "micro/recall": 0.6896730669434354, "micro/precision": 0.8148375229920294, "macro/f1": 0.7470489038785835, "macro/f1_ci": {}, "macro/recall": 0.6896730669434354, "macro/precision": 0.8148375229920294}, "2020.dev (span detection)": {"micro/f1": 0.7472150814053127, "micro/f1_ci": {}, "micro/recall": 0.6833855799373041, "micro/precision": 0.8241965973534972, "macro/f1": 0.7472150814053127, "macro/f1_ci": {}, "macro/recall": 0.6833855799373041, "macro/precision": 0.8241965973534972}}
+{"2021.dev": {"micro/f1": 0.6360351058337637, "micro/f1_ci": {}, "micro/recall": 0.616, "micro/precision": 0.6574172892209178, "macro/f1": 0.5912051787344677, "macro/f1_ci": {}, "macro/recall": 0.5716765665918595, "macro/precision": 0.6145258341593257, "per_entity_metric": {"corporation": {"f1": 0.5235602094240838, "f1_ci": {}, "precision": 0.5617977528089888, "recall": 0.49019607843137253}, "creative_work": {"f1": 0.5, "f1_ci": {}, "precision": 0.48717948717948717, "recall": 0.5135135135135135}, "event": {"f1": 0.35684647302904565, "f1_ci": {}, "precision": 0.39090909090909093, "recall": 0.3282442748091603}, "group": {"f1": 0.627906976744186, "f1_ci": {}, "precision": 0.6650246305418719, "recall": 0.5947136563876652}, "location": {"f1": 0.6818181818181818, "f1_ci": {}, "precision": 0.75, "recall": 0.625}, "person": {"f1": 0.8301225919439579, "f1_ci": {}, "precision": 0.8229166666666666, "recall": 0.8374558303886925}, "product": {"f1": 0.6181818181818182, "f1_ci": {}, "precision": 0.6238532110091743, "recall": 0.6126126126126126}}}, "2021.test": {"micro/f1": 0.6404513989878424, "micro/f1_ci": {"90": [0.6310532748860292, 0.6500710194412829], "95": [0.6296658889111393, 0.6521427599284435]}, "micro/recall": 0.6365633672525439, "micro/precision": 0.6443872176050568, "macro/f1": 0.5910583983096561, "macro/f1_ci": {"90": [0.5809463231552521, 0.6010049606712689], "95": [0.5788166178408317, 0.6032882856914171]}, "macro/recall": 0.5900571634271187, "macro/precision": 0.5928837696021392, "per_entity_metric": {"corporation": {"f1": 0.5058236272878537, "f1_ci": {"90": [0.48221203045637623, 0.5303888996856597], "95": [0.4768192669028184, 0.5361739312316256]}, "precision": 0.5049833887043189, "recall": 0.5066666666666667}, "creative_work": {"f1": 0.43911917098445596, "f1_ci": {"90": [0.4088519263305804, 0.4698779572211306], "95": [0.4033908658729188, 0.47548628801170667]}, "precision": 0.41697416974169743, "recall": 0.4637482900136799}, "event": {"f1": 0.46597353497164457, "f1_ci": {"90": [0.4414376523975732, 0.48765845692109383], "95": [0.4374048509297999, 0.49298079426045754]}, "precision": 0.48475909537856443, "recall": 0.44858962693357596}, "group": {"f1": 0.6068318821165438, "f1_ci": {"90": [0.5857613197870366, 0.6284661621519472], "95": [0.5822767750520318, 0.6337291179191381]}, "precision": 0.6171662125340599, "recall": 0.5968379446640316}, "location": {"f1": 0.6398910823689584, "f1_ci": {"90": [0.61063908109445, 0.6675512121611009], "95": [0.6064278122897154, 0.6741361629127748]}, "precision": 0.6241699867197875, "recall": 0.6564245810055865}, "person": {"f1": 0.8267511177347244, "f1_ci": {"90": [0.8157005907020787, 0.8380098885018492], "95": [0.8137865601171665, 0.8400948145156062]}, "precision": 0.8354668674698795, "recall": 0.8182153392330384}, "product": {"f1": 0.6530183727034121, "f1_ci": {"90": [0.6302189400687924, 0.6751343003974581], "95": [0.6264020156559537, 0.6791711660773018]}, "precision": 0.6666666666666666, "recall": 0.6399176954732511}}}, "2020.test": {"micro/f1": 0.6335644937586686, "micro/f1_ci": {"90": [0.6120421464705215, 0.6525076828761172], "95": [0.6086564713285258, 0.6559915040520051]}, "micro/recall": 0.5926310326933056, "micro/precision": 0.6805721096543504, "macro/f1": 0.5914520478690088, "macro/f1_ci": {"90": [0.5672890790149243, 0.6111046076343697], "95": [0.5631922824822733, 0.615969012049981]}, "macro/recall": 0.5535477989961968, "macro/precision": 0.6370623744887871, "per_entity_metric": {"corporation": {"f1": 0.5322128851540617, "f1_ci": {"90": [0.4679528605099636, 0.5855111633372503], "95": [0.45919247230614296, 0.5964937200956938]}, "precision": 0.572289156626506, "recall": 0.4973821989528796}, "creative_work": {"f1": 0.4941176470588235, "f1_ci": {"90": [0.4324237140366173, 0.5483963133640553], "95": [0.4233767507552276, 0.5575498000792478]}, "precision": 0.5217391304347826, "recall": 0.4692737430167598}, "event": {"f1": 0.46613545816733065, "f1_ci": {"90": [0.41300613255759094, 0.5199418408061135], "95": [0.40350089295094027, 0.5281582054309327]}, "precision": 0.4936708860759494, "recall": 0.44150943396226416}, "group": {"f1": 0.5464684014869888, "f1_ci": {"90": [0.4933666798613359, 0.5976370403789758], "95": [0.4788116130430073, 0.610861672409387]}, "precision": 0.6475770925110133, "recall": 0.47266881028938906}, "location": {"f1": 0.63125, "f1_ci": {"90": [0.5671345820472707, 0.6885394482690307], "95": [0.5551672761749965, 0.7014767828550316]}, "precision": 0.6516129032258065, "recall": 0.6121212121212121}, "person": {"f1": 0.81326352530541, "f1_ci": {"90": [0.7841960889038811, 0.8395792418896547], "95": [0.7788274499501572, 0.8438129923423588]}, "precision": 0.8472727272727273, "recall": 0.7818791946308725}, "product": {"f1": 0.6567164179104477, "f1_ci": {"90": [0.6008587786259542, 0.7132317854013615], "95": [0.5929074717150218, 0.7208718442447583]}, "precision": 0.7252747252747253, "recall": 0.6}}}, "2021.test (span detection)": {"micro/f1": 0.7770796974985457, "micro/f1_ci": {}, "micro/recall": 0.7724066150109865, "micro/precision": 0.7818096687346365, "macro/f1": 0.7770796974985457, "macro/f1_ci": {}, "macro/recall": 0.7724066150109865, "macro/precision": 0.7818096687346365}, "2020.test (span detection)": {"micro/f1": 0.7436182019977802, "micro/f1_ci": {}, "micro/recall": 0.6953814218993254, "micro/precision": 0.7990459153249851, "macro/f1": 0.7436182019977802, "macro/f1_ci": {}, "macro/recall": 0.6953814218993254, "macro/precision": 0.7990459153249851}}

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/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": "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}