model update

config.json

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

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6220703125000001, "micro/f1_ci": {}, "micro/recall": 0.637, "micro/precision": 0.607824427480916, "macro/f1": 0.5734483206270202, "macro/f1_ci": {}, "macro/recall": 0.5876986774163436, "macro/precision": 0.5610235583875315, "per_entity_metric": {"corporation": {"f1": 0.5217391304347826, "f1_ci": {}, "precision": 0.5142857142857142, "recall": 0.5294117647058824}, "creative_work": {"f1": 0.45333333333333337, "f1_ci": {}, "precision": 0.4473684210526316, "recall": 0.4594594594594595}, "event": {"f1": 0.38247011952191234, "f1_ci": {}, "precision": 0.4, "recall": 0.366412213740458}, "group": {"f1": 0.6214442013129103, "f1_ci": {}, "precision": 0.6173913043478261, "recall": 0.6255506607929515}, "location": {"f1": 0.6184210526315789, "f1_ci": {}, "precision": 0.5875, "recall": 0.6527777777777778}, "person": {"f1": 0.8006589785831961, "f1_ci": {}, "precision": 0.75, "recall": 0.8586572438162544}, "product": {"f1": 0.6160714285714285, "f1_ci": {}, "precision": 0.6106194690265486, "recall": 0.6216216216216216}}}, "2021.test": {"micro/f1": 0.6308962917798349, "micro/f1_ci": {"90": [0.6218627510838193, 0.6407164862470697], "95": [0.6201627010426306, 0.6422908401462293]}, "micro/recall": 0.6580712303422757, "micro/precision": 0.6058767167039285, "macro/f1": 0.5735468406550763, "macro/f1_ci": {"90": [0.5633518872919319, 0.5834141537051213], "95": [0.5619155878559741, 0.585359923196132]}, "macro/recall": 0.6012922054817469, "macro/precision": 0.5503198173085064, "per_entity_metric": {"corporation": {"f1": 0.4565701559020044, "f1_ci": {"90": [0.43122213480199306, 0.4842832655545205], "95": [0.422987517373063, 0.4892101769228394]}, "precision": 0.4575892857142857, "recall": 0.45555555555555555}, "creative_work": {"f1": 0.4098984771573604, "f1_ci": {"90": [0.3791530120969373, 0.4415152462146761], "95": [0.3716394651460033, 0.4462899138884782]}, "precision": 0.38224852071005916, "recall": 0.4418604651162791}, "event": {"f1": 0.4628410159924742, "f1_ci": {"90": [0.43764436774212423, 0.4844905070216916], "95": [0.4327500906125407, 0.49103704697586353]}, "precision": 0.4790652385589094, "recall": 0.44767970882620567}, "group": {"f1": 0.593177511054959, "f1_ci": {"90": [0.5717044673748471, 0.6144093322442311], "95": [0.5676831336909995, 0.6175847266352983]}, "precision": 0.5697815533980582, "recall": 0.6185770750988142}, "location": {"f1": 0.6333949476278496, "f1_ci": {"90": [0.6061374762309342, 0.6596729625322199], "95": [0.5999818181818181, 0.6642491807610421]}, "precision": 0.5667034178610805, "recall": 0.7178770949720671}, "person": {"f1": 0.8279457768508863, "f1_ci": {"90": [0.8177849742494966, 0.8392861816686192], "95": [0.8161339468587502, 0.8409499904355973]}, "precision": 0.7830374753451677, "recall": 0.8783185840707964}, "product": {"f1": 0.631, "f1_ci": {"90": [0.6078329186866498, 0.6538099694036692], "95": [0.602711796196466, 0.6565176505572475]}, "precision": 0.6138132295719845, "recall": 0.6491769547325102}}}, "2020.test": {"micro/f1": 0.6205787781350482, "micro/f1_ci": {"90": [0.5990600374135929, 0.641028413028413], "95": [0.5956429008859256, 0.645577807233236]}, "micro/recall": 0.6009340944473275, "micro/precision": 0.6415512465373961, "macro/f1": 0.5723158793505982, "macro/f1_ci": {"90": [0.5491541277371618, 0.593824224484208], "95": [0.5446730617743423, 0.5989182517444881]}, "macro/recall": 0.5568451570610017, "macro/precision": 0.5910271170769507, "per_entity_metric": {"corporation": {"f1": 0.49867374005305043, "f1_ci": {"90": [0.4362597402597403, 0.5552962052962053], "95": [0.4225177366931115, 0.5675940646528883]}, "precision": 0.5053763440860215, "recall": 0.49214659685863876}, "creative_work": {"f1": 0.4583333333333333, "f1_ci": {"90": [0.3903903903903904, 0.516321444502628], "95": [0.3776601932639084, 0.5297937192118228]}, "precision": 0.49044585987261147, "recall": 0.4301675977653631}, "event": {"f1": 0.43892339544513453, "f1_ci": {"90": [0.38343874372946507, 0.4931036128685116], "95": [0.3732780599111177, 0.5052203054609383]}, "precision": 0.48623853211009177, "recall": 0.4}, "group": {"f1": 0.5264957264957265, "f1_ci": {"90": [0.4739659822849217, 0.5779008444686745], "95": [0.4623267883150051, 0.5874770558415155]}, "precision": 0.5620437956204379, "recall": 0.49517684887459806}, "location": {"f1": 0.6358381502890174, "f1_ci": {"90": [0.5734652877656781, 0.6918347805270832], "95": [0.5622911498701775, 0.7034883720930232]}, "precision": 0.6077348066298343, "recall": 0.6666666666666666}, "person": {"f1": 0.81787521079258, "f1_ci": {"90": [0.7927999152425893, 0.8405389863292992], "95": [0.7873498023715415, 0.844675509305848]}, "precision": 0.8220338983050848, "recall": 0.8137583892617449}, "product": {"f1": 0.630071599045346, "f1_ci": {"90": [0.5727563482336753, 0.683606306263845], "95": [0.5630568382452805, 0.6948397887323944]}, "precision": 0.6633165829145728, "recall": 0.6}}}, "2021.test (span detection)": {"micro/f1": 0.7788214245778822, "micro/f1_ci": {}, "micro/recall": 0.8054816699433329, "micro/precision": 0.7538694663924668, "macro/f1": 0.7788214245778822, "macro/f1_ci": {}, "macro/recall": 0.8054816699433329, "macro/precision": 0.7538694663924668}, "2020.test (span detection)": {"micro/f1": 0.7595141700404859, "micro/f1_ci": {}, "micro/recall": 0.7301504929942917, "micro/precision": 0.7913385826771654, "macro/f1": 0.7595141700404859, "macro/f1_ci": {}, "macro/recall": 0.7301504929942917, "macro/precision": 0.7913385826771654}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0fa0e284877dd585ffbe4ca4a73436c4a36cede2dd4d7f0f18bda9ed60519f1
-size 537363441
+oid sha256:66ff084ebd0d14d2e826d12d6104d2e34ac1efb38bb26468508a6633a1c844ae
+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/best_model", "special_tokens_map_file": "cner_output/model/baseline_2021/bertweet_base/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": "2021.train", "model": "vinai/bertweet-base", "crf": false, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 0.0001, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}