model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/t_roberta_base_2019/best_model",
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-2019-90m",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6266882766072394, "micro/f1_ci": {}, "micro/recall": 0.58, "micro/precision": 0.681551116333725, "macro/f1": 0.5706545991586711, "macro/f1_ci": {}, "macro/recall": 0.531585091469556, "macro/precision": 0.6312766832243282, "per_entity_metric": {"corporation": {"f1": 0.5360824742268041, "f1_ci": {}, "precision": 0.5652173913043478, "recall": 0.5098039215686274}, "creative_work": {"f1": 0.4406779661016949, "f1_ci": {}, "precision": 0.5909090909090909, "recall": 0.35135135135135137}, "event": {"f1": 0.4192139737991266, "f1_ci": {}, "precision": 0.4897959183673469, "recall": 0.366412213740458}, "group": {"f1": 0.6036745406824147, "f1_ci": {}, "precision": 0.7467532467532467, "recall": 0.5066079295154186}, "location": {"f1": 0.5844155844155844, "f1_ci": {}, "precision": 0.5487804878048781, "recall": 0.625}, "person": {"f1": 0.8145580589254766, "f1_ci": {}, "precision": 0.7993197278911565, "recall": 0.8303886925795053}, "product": {"f1": 0.5959595959595959, "f1_ci": {}, "precision": 0.6781609195402298, "recall": 0.5315315315315315}}}, "2021.test": {"micro/f1": 0.6323179293083451, "micro/f1_ci": {"90": [0.6233520895930195, 0.6418683671749849], "95": [0.6212129239683746, 0.6433834953337656]}, "micro/recall": 0.5988667900092507, "micro/precision": 0.669727143411354, "macro/f1": 0.5671647388688191, "macro/f1_ci": {"90": [0.5572399048719903, 0.577247635111665], "95": [0.5553732615109348, 0.5793881693393761]}, "macro/recall": 0.5439217682783225, "macro/precision": 0.6049623231784063, "per_entity_metric": {"corporation": {"f1": 0.4673109721432633, "f1_ci": {"90": [0.44073821638214794, 0.49380346194506486], "95": [0.4345049629782454, 0.5010802868149081]}, "precision": 0.47846332945285214, "recall": 0.45666666666666667}, "creative_work": {"f1": 0.33124018838304553, "f1_ci": {"90": [0.30036395978888, 0.3626835949872128], "95": [0.29519152771518703, 0.3685301988871562]}, "precision": 0.3885819521178637, "recall": 0.28864569083447333}, "event": {"f1": 0.4597107438016529, "f1_ci": {"90": [0.43358831070137327, 0.4834637283006848], "95": [0.429486076821645, 0.48853823770491805]}, "precision": 0.5316606929510155, "recall": 0.4049135577797998}, "group": {"f1": 0.5760869565217391, "f1_ci": {"90": [0.5533624070508728, 0.6002919737979431], "95": [0.5506175388446288, 0.6050261925906731]}, "precision": 0.7013232514177694, "recall": 0.4888010540184453}, "location": {"f1": 0.6441717791411042, "f1_ci": {"90": [0.6165992673657916, 0.6703458808896694], "95": [0.6119444333644128, 0.6748159083550472]}, "precision": 0.574398249452954, "recall": 0.7332402234636871}, "person": {"f1": 0.8321060382916053, "f1_ci": {"90": [0.821677267531769, 0.8427002490386487], "95": [0.8194743155293102, 0.8450823127765467]}, "precision": 0.8308823529411765, "recall": 0.8333333333333334}, "product": {"f1": 0.6595264937993236, "f1_ci": {"90": [0.6365520783180869, 0.6811715301378959], "95": [0.63347027394072, 0.6853053837030515]}, "precision": 0.729426433915212, "recall": 0.6018518518518519}}}, "2020.test": {"micro/f1": 0.6190614981055086, "micro/f1_ci": {"90": [0.5980767583769521, 0.6386591052606013], "95": [0.594361748617247, 0.6421009828807712]}, "micro/recall": 0.5511157239231966, "micro/precision": 0.7061170212765957, "macro/f1": 0.560944714651875, "macro/f1_ci": {"90": [0.5382449708194087, 0.5830707544345507], "95": [0.5329546485473574, 0.5877732547723248]}, "macro/recall": 0.5048039912609852, "macro/precision": 0.6527607933480432, "per_entity_metric": {"corporation": {"f1": 0.48587570621468923, "f1_ci": {"90": [0.4244097956307259, 0.5391095780737103], "95": [0.4135752506857322, 0.5517241379310345]}, "precision": 0.5276073619631901, "recall": 0.450261780104712}, "creative_work": {"f1": 0.4109589041095891, "f1_ci": {"90": [0.34865740740740736, 0.4698943140984992], "95": [0.3368421052631579, 0.4780009260331057]}, "precision": 0.5309734513274337, "recall": 0.33519553072625696}, "event": {"f1": 0.44345898004434586, "f1_ci": {"90": [0.38608838826019914, 0.49776446992488316], "95": [0.3770863852083504, 0.5061822739770339]}, "precision": 0.5376344086021505, "recall": 0.37735849056603776}, "group": {"f1": 0.4956896551724138, "f1_ci": {"90": [0.43870042305658385, 0.5517481398511882], "95": [0.42508749495221426, 0.5630294024483409]}, "precision": 0.7516339869281046, "recall": 0.36977491961414793}, "location": {"f1": 0.6416184971098265, "f1_ci": {"90": [0.5747673429813478, 0.7], "95": [0.5628215866937897, 0.7102204062256282]}, "precision": 0.6132596685082873, "recall": 0.6727272727272727}, "person": {"f1": 0.8230165649520488, "f1_ci": {"90": [0.7955670228304957, 0.8472247474747475], "95": [0.7889798131252806, 0.8509595090840202]}, "precision": 0.8566243194192378, "recall": 0.7919463087248322}, "product": {"f1": 0.6259946949602122, "f1_ci": {"90": [0.5654336444343274, 0.6793460715738638], "95": [0.5555480682839173, 0.6876914070924608]}, "precision": 0.7515923566878981, "recall": 0.5363636363636364}}}, "2021.test (span detection)": {"micro/f1": 0.756898656898657, "micro/f1_ci": {}, "micro/recall": 0.716896033306349, "micro/precision": 0.801629380576749, "macro/f1": 0.756898656898657, "macro/f1_ci": {}, "macro/recall": 0.716896033306349, "macro/precision": 0.801629380576749}, "2020.test (span detection)": {"micro/f1": 0.7303993004954824, "micro/f1_ci": {}, "micro/recall": 0.6502335236118318, "micro/precision": 0.8331117021276596, "macro/f1": 0.7303993004954824, "macro/f1_ci": {}, "macro/recall": 0.6502335236118318, "macro/precision": 0.8331117021276596}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa37c9ca1b100279151b2d0b1e7e697c4cc60621d9330d23d7e2fe13cab740cd
-size 496349169
+oid sha256:fdc5a1c3a0cced26a97ccbcc1421fa839da2093aa43821a3413a45f079e96e47
+size 496351921

tokenizer_config.json

@@ -1 +1 @@
-{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cner_output/model/baseline_2021/t_roberta_base_2019/best_model", "tokenizer_class": "RobertaTokenizer"}
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cardiffnlp/twitter-roberta-base-2019-90m", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2021.train", "model": "cardiffnlp/twitter-roberta-base-2019-90m", "crf": true, "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}