model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/bert_large_concat/best_model",
+  "_name_or_path": "bert-large-cased",
   "architectures": [
     "BertForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6309464196294442, "micro/f1_ci": {}, "micro/recall": 0.63, "micro/precision": 0.6318956870611836, "macro/f1": 0.5854681564149163, "macro/f1_ci": {}, "macro/recall": 0.5839910318311838, "macro/precision": 0.5894227103402361, "per_entity_metric": {"corporation": {"f1": 0.5767441860465116, "f1_ci": {}, "precision": 0.5486725663716814, "recall": 0.6078431372549019}, "creative_work": {"f1": 0.44025157232704404, "f1_ci": {}, "precision": 0.4117647058823529, "recall": 0.47297297297297297}, "event": {"f1": 0.41666666666666663, "f1_ci": {}, "precision": 0.41353383458646614, "recall": 0.4198473282442748}, "group": {"f1": 0.634920634920635, "f1_ci": {}, "precision": 0.6542056074766355, "recall": 0.6167400881057269}, "location": {"f1": 0.582089552238806, "f1_ci": {}, "precision": 0.6290322580645161, "recall": 0.5416666666666666}, "person": {"f1": 0.809106830122592, "f1_ci": {}, "precision": 0.8020833333333334, "recall": 0.8162544169611308}, "product": {"f1": 0.6384976525821596, "f1_ci": {}, "precision": 0.6666666666666666, "recall": 0.6126126126126126}}}, "2021.test": {"micro/f1": 0.6358014184397163, "micro/f1_ci": {"90": [0.626687324917235, 0.6449412548744916], "95": [0.6246460521646338, 0.6465123623688929]}, "micro/recall": 0.647895467160037, "micro/precision": 0.6241506071070514, "macro/f1": 0.5900128438830615, "macro/f1_ci": {"90": [0.5803525272420662, 0.5998813669168028], "95": [0.5788003497848505, 0.601259279937617]}, "macro/recall": 0.6041427086183797, "macro/precision": 0.5789290375636192, "per_entity_metric": {"corporation": {"f1": 0.5013333333333333, "f1_ci": {"90": [0.4773041121935053, 0.5251458394589827], "95": [0.47212530903053357, 0.5299806250616865]}, "precision": 0.48205128205128206, "recall": 0.5222222222222223}, "creative_work": {"f1": 0.4016441573693482, "f1_ci": {"90": [0.3726155462184874, 0.4322116501076389], "95": [0.3661632723388598, 0.4400077984403119]}, "precision": 0.35185185185185186, "recall": 0.46785225718194257}, "event": {"f1": 0.47004180213655367, "f1_ci": {"90": [0.44757361821728175, 0.49203100743385103], "95": [0.4413532011324317, 0.49699281439717774]}, "precision": 0.48007590132827327, "recall": 0.4604185623293904}, "group": {"f1": 0.5973851827019778, "f1_ci": {"90": [0.5768783472459447, 0.6186116613189769], "95": [0.5739186663249559, 0.6234884659948738]}, "precision": 0.6081911262798635, "recall": 0.5869565217391305}, "location": {"f1": 0.6720321931589538, "f1_ci": {"90": [0.6440601569406398, 0.6977364758273161], "95": [0.6338632755879807, 0.7029718042123281]}, "precision": 0.6464516129032258, "recall": 0.6997206703910615}, "person": {"f1": 0.8185623293903548, "f1_ci": {"90": [0.8069829934867924, 0.8294376799389931], "95": [0.8044913837616584, 0.8315346050035313]}, "precision": 0.8081207330219188, "recall": 0.8292772861356932}, "product": {"f1": 0.6690909090909091, "f1_ci": {"90": [0.6468565841312396, 0.6917961840792326], "95": [0.6434676970626467, 0.6968318058220542]}, "precision": 0.6757607555089192, "recall": 0.6625514403292181}}}, "2020.test": {"micro/f1": 0.6248982912937348, "micro/f1_ci": {"90": [0.6036183066759389, 0.6448988322002785], "95": [0.5997215835288842, 0.6486262984430212]}, "micro/recall": 0.5978204462895693, "micro/precision": 0.6545454545454545, "macro/f1": 0.5862888361879851, "macro/f1_ci": {"90": [0.5625855374311386, 0.6074574296186365], "95": [0.5597026514157946, 0.6122702483863757]}, "macro/recall": 0.5608699203922957, "macro/precision": 0.616927771523058, "per_entity_metric": {"corporation": {"f1": 0.5555555555555557, "f1_ci": {"90": [0.4929666282756757, 0.6157425077749504], "95": [0.4815702026201889, 0.6239593828404353]}, "precision": 0.5614973262032086, "recall": 0.5497382198952879}, "creative_work": {"f1": 0.47645429362880887, "f1_ci": {"90": [0.41873557692307695, 0.531952314765316], "95": [0.4105496653883751, 0.5422103927516406]}, "precision": 0.4725274725274725, "recall": 0.48044692737430167}, "event": {"f1": 0.4307692307692308, "f1_ci": {"90": [0.3765041888804265, 0.48304065137052626], "95": [0.3662964004499437, 0.4933740655220503]}, "precision": 0.4392156862745098, "recall": 0.4226415094339623}, "group": {"f1": 0.5488029465930019, "f1_ci": {"90": [0.49312550362610796, 0.6021388689955173], "95": [0.4815344237631145, 0.6138935323507213]}, "precision": 0.6422413793103449, "recall": 0.4790996784565916}, "location": {"f1": 0.6389776357827476, "f1_ci": {"90": [0.5704350369233019, 0.6954414208174869], "95": [0.5592458090141159, 0.7055226928772518]}, "precision": 0.6756756756756757, "recall": 0.6060606060606061}, "person": {"f1": 0.8030954428202924, "f1_ci": {"90": [0.7764797488787779, 0.8275862068965517], "95": [0.7715901091859506, 0.8317556848228449]}, "precision": 0.8236331569664903, "recall": 0.7835570469798657}, "product": {"f1": 0.6503667481662592, "f1_ci": {"90": [0.5995089521794967, 0.6982585104933628], "95": [0.5893208083725082, 0.7077953136504405]}, "precision": 0.7037037037037037, "recall": 0.6045454545454545}}}, "2021.test (span detection)": {"micro/f1": 0.7721468702116793, "micro/f1_ci": {}, "micro/recall": 0.7867468486180178, "micro/precision": 0.7580788945843548, "macro/f1": 0.7721468702116793, "macro/f1_ci": {}, "macro/recall": 0.7867468486180178, "macro/precision": 0.7580788945843548}, "2020.test (span detection)": {"micro/f1": 0.7357569180683668, "micro/f1_ci": {}, "micro/recall": 0.7036844836533471, "micro/precision": 0.770892552586697, "macro/f1": 0.7357569180683668, "macro/f1_ci": {}, "macro/recall": 0.7036844836533471, "macro/precision": 0.770892552586697}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d967e8d62526c58546478ba572c8905f3a2a48244d61c9476ece60dfcb334fd
-size 1330337393
+oid sha256:da8c3d86a8f9a3ae7b2874d92597a5973bdf9d0993f7fc2d1b4b6080f3899d16
+size 1330342897

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "cner_output/model/baseline_2021/bert_large_concat/best_model", "special_tokens_map_file": "cner_output/model/baseline_2021/bert_large_concat/best_model/special_tokens_map.json", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2020_2021.train", "model": "bert-large-cased", "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}