model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/bertweet_base_concat/best_model",
+  "_name_or_path": "vinai/bertweet-base",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6479289940828402, "micro/f1_ci": {}, "micro/recall": 0.657, "micro/precision": 0.6391050583657587, "macro/f1": 0.6043271222909856, "macro/f1_ci": {}, "macro/recall": 0.6132417907641617, "macro/precision": 0.5968927910350338, "per_entity_metric": {"corporation": {"f1": 0.5603864734299516, "f1_ci": {}, "precision": 0.5523809523809524, "recall": 0.5686274509803921}, "creative_work": {"f1": 0.48407643312101906, "f1_ci": {}, "precision": 0.4578313253012048, "recall": 0.5135135135135135}, "event": {"f1": 0.4528301886792453, "f1_ci": {}, "precision": 0.44776119402985076, "recall": 0.4580152671755725}, "group": {"f1": 0.6269315673289183, "f1_ci": {}, "precision": 0.6283185840707964, "recall": 0.6255506607929515}, "location": {"f1": 0.6442953020134228, "f1_ci": {}, "precision": 0.6233766233766234, "recall": 0.6666666666666666}, "person": {"f1": 0.8361774744027305, "f1_ci": {}, "precision": 0.8085808580858086, "recall": 0.8657243816254417}, "product": {"f1": 0.6255924170616114, "f1_ci": {}, "precision": 0.66, "recall": 0.5945945945945946}}}, "2021.test": {"micro/f1": 0.6536203522504892, "micro/f1_ci": {"90": [0.6447872756148977, 0.6633207283107695], "95": [0.6425923702362265, 0.6650666703489687]}, "micro/recall": 0.6758788159111934, "micro/precision": 0.6327812060192703, "macro/f1": 0.6052211252463111, "macro/f1_ci": {"90": [0.5954577789975593, 0.6145053233650972], "95": [0.5935811679603806, 0.6159321952528645]}, "macro/recall": 0.6302754427289782, "macro/precision": 0.5838227039402247, "per_entity_metric": {"corporation": {"f1": 0.5250836120401337, "f1_ci": {"90": [0.499114468582439, 0.5502487923745039], "95": [0.49402204164639574, 0.5542265421428756]}, "precision": 0.5268456375838926, "recall": 0.5233333333333333}, "creative_work": {"f1": 0.4653774173424829, "f1_ci": {"90": [0.4350066554677983, 0.4944221755636148], "95": [0.42865964754879954, 0.5003082860885536]}, "precision": 0.42775229357798167, "recall": 0.5102599179206566}, "event": {"f1": 0.4805781391147245, "f1_ci": {"90": [0.45876392113230563, 0.5025502448910658], "95": [0.4547767349386974, 0.5085979655019902]}, "precision": 0.47713004484304933, "recall": 0.4840764331210191}, "group": {"f1": 0.6033376123234916, "f1_ci": {"90": [0.5833319019809917, 0.6255975435188365], "95": [0.5807051025464135, 0.6290415081557142]}, "precision": 0.5882352941176471, "recall": 0.619235836627141}, "location": {"f1": 0.6567164179104478, "f1_ci": {"90": [0.6289343271359739, 0.6827299264868976], "95": [0.6232678042111391, 0.6866568408235075]}, "precision": 0.5919282511210763, "recall": 0.7374301675977654}, "person": {"f1": 0.8408236347358997, "f1_ci": {"90": [0.8306288526403558, 0.8509253313521083], "95": [0.8287685929940346, 0.8526699869564047]}, "precision": 0.8172641837800209, "recall": 0.8657817109144543}, "product": {"f1": 0.6646310432569975, "f1_ci": {"90": [0.642891431340614, 0.6874707012510687], "95": [0.6397193439875759, 0.6905268361734545]}, "precision": 0.6576032225579054, "recall": 0.6718106995884774}}}, "2020.test": {"micro/f1": 0.6574172892209178, "micro/f1_ci": {"90": [0.6362605912738951, 0.6776829185560604], "95": [0.6329381337554338, 0.681496695257187]}, "micro/recall": 0.6393357550596782, "micro/precision": 0.6765513454146074, "macro/f1": 0.6161494551388561, "macro/f1_ci": {"90": [0.5922560215720907, 0.6371588233814224], "95": [0.5874972325138178, 0.6433530990576218]}, "macro/recall": 0.6030680287240185, "macro/precision": 0.6335227896210995, "per_entity_metric": {"corporation": {"f1": 0.5721925133689839, "f1_ci": {"90": [0.5118543960209868, 0.627970887027902], "95": [0.5013, 0.6377742851758119]}, "precision": 0.5846994535519126, "recall": 0.5602094240837696}, "creative_work": {"f1": 0.5409836065573771, "f1_ci": {"90": [0.4857961799177999, 0.593859943977591], "95": [0.4738351063829787, 0.6035510525280346]}, "precision": 0.5294117647058824, "recall": 0.553072625698324}, "event": {"f1": 0.48554913294797686, "f1_ci": {"90": [0.43302563132507327, 0.5353292120908344], "95": [0.42145597637198395, 0.5447158512340591]}, "precision": 0.49606299212598426, "recall": 0.47547169811320755}, "group": {"f1": 0.5734767025089605, "f1_ci": {"90": [0.519707990723171, 0.6271215968818284], "95": [0.5103473314135293, 0.6346256684491981]}, "precision": 0.6477732793522267, "recall": 0.5144694533762058}, "location": {"f1": 0.6457142857142857, "f1_ci": {"90": [0.5746137178098175, 0.7090515682906987], "95": [0.5604067645282423, 0.7207259585166563]}, "precision": 0.6108108108108108, "recall": 0.6848484848484848}, "person": {"f1": 0.8415672913117546, "f1_ci": {"90": [0.8160757025086428, 0.8660040531276134], "95": [0.8116914027938739, 0.8688960711564506]}, "precision": 0.8546712802768166, "recall": 0.8288590604026845}, "product": {"f1": 0.6535626535626535, "f1_ci": {"90": [0.6015352256997502, 0.7024343440641215], "95": [0.5921931733188277, 0.711786009526434]}, "precision": 0.7112299465240641, "recall": 0.6045454545454545}}}, "2021.test (span detection)": {"micro/f1": 0.7898680384701409, "micro/f1_ci": {}, "micro/recall": 0.8168150803746964, "micro/precision": 0.7646421998484356, "macro/f1": 0.7898680384701409, "macro/f1_ci": {}, "macro/recall": 0.8168150803746964, "macro/precision": 0.7646421998484356}, "2020.test (span detection)": {"micro/f1": 0.7691486522551374, "micro/f1_ci": {}, "micro/recall": 0.7477944992215879, "micro/precision": 0.7917582417582417, "macro/f1": 0.7691486522551374, "macro/f1_ci": {}, "macro/recall": 0.7477944992215879, "macro/precision": 0.7917582417582417}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8d3d95917f3299839ed2d293751566e3ee7a79175c01395365f11ca5f9094e
-size 537363441
+oid sha256:c619ba0bed513cb4d30f6608e3c6c448e73dc7be63fdf6f84ad986daefc29717
+size 537366193

tokenizer_config.json

@@ -1 +1 @@
-{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "name_or_path": "cner_output/model/baseline_2021/bertweet_base_concat/best_model", "special_tokens_map_file": "cner_output/model/baseline_2021/bertweet_base_concat/best_model/special_tokens_map.json", "tokenizer_class": "BertweetTokenizer"}
+{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "name_or_path": "vinai/bertweet-base", "tokenizer_class": "BertweetTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2020_2021.train", "model": "vinai/bertweet-base", "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}