model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/t_roberta_base_2019_continuous/best_model",
+  "_name_or_path": "tner/twitter-roberta-base-2019-90m-tweetner-2020",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6450261780104712, "micro/f1_ci": {}, "micro/recall": 0.616, "micro/precision": 0.676923076923077, "macro/f1": 0.5962535580648441, "macro/f1_ci": {}, "macro/recall": 0.5745880129991789, "macro/precision": 0.6251527330747371, "per_entity_metric": {"corporation": {"f1": 0.5797101449275363, "f1_ci": {}, "precision": 0.5714285714285714, "recall": 0.5882352941176471}, "creative_work": {"f1": 0.4697986577181208, "f1_ci": {}, "precision": 0.4666666666666667, "recall": 0.47297297297297297}, "event": {"f1": 0.4067796610169492, "f1_ci": {}, "precision": 0.45714285714285713, "recall": 0.366412213740458}, "group": {"f1": 0.6305418719211824, "f1_ci": {}, "precision": 0.7150837988826816, "recall": 0.5638766519823789}, "location": {"f1": 0.5945945945945946, "f1_ci": {}, "precision": 0.5789473684210527, "recall": 0.6111111111111112}, "person": {"f1": 0.8324514991181658, "f1_ci": {}, "precision": 0.8309859154929577, "recall": 0.833922261484099}, "product": {"f1": 0.6598984771573604, "f1_ci": {}, "precision": 0.7558139534883721, "recall": 0.5855855855855856}}}, "2021.test": {"micro/f1": 0.6587179789871326, "micro/f1_ci": {"90": [0.6500084574752211, 0.6675327789934176], "95": [0.6480876172354417, 0.6695072839398589]}, "micro/recall": 0.6452358926919519, "micro/precision": 0.6727755003617073, "macro/f1": 0.6107285696131857, "macro/f1_ci": {"90": [0.6016803308717976, 0.6202645433833436], "95": [0.5994476476393031, 0.6216597508490829]}, "macro/recall": 0.6039860329938679, "macro/precision": 0.6215631908472189, "per_entity_metric": {"corporation": {"f1": 0.5165775401069518, "f1_ci": {"90": [0.49149727683928734, 0.5424631455686919], "95": [0.4852586317545886, 0.5461513660625363]}, "precision": 0.4979381443298969, "recall": 0.5366666666666666}, "creative_work": {"f1": 0.480106100795756, "f1_ci": {"90": [0.453073041723214, 0.50950812525732], "95": [0.4466713194941541, 0.5161499273646297]}, "precision": 0.46589446589446587, "recall": 0.4952120383036936}, "event": {"f1": 0.4846715328467153, "f1_ci": {"90": [0.461685794044665, 0.5075673834488479], "95": [0.45719391471483367, 0.5126992651593725]}, "precision": 0.5209205020920502, "recall": 0.4531392174704277}, "group": {"f1": 0.6041666666666665, "f1_ci": {"90": [0.5830811998193606, 0.6264368818381182], "95": [0.5783034453510499, 0.6304740494329455]}, "precision": 0.6642969984202212, "recall": 0.5540184453227931}, "location": {"f1": 0.6836268754076973, "f1_ci": {"90": [0.6571241349182627, 0.709613327872738], "95": [0.6521909682357443, 0.7150913388648733]}, "precision": 0.6413708690330477, "recall": 0.7318435754189944}, "person": {"f1": 0.8458527493010252, "f1_ci": {"90": [0.8342425995098203, 0.8575205549845837], "95": [0.8314334208846303, 0.8595415243945875]}, "precision": 0.8552581982661138, "recall": 0.8366519174041298}, "product": {"f1": 0.6600985221674878, "f1_ci": {"90": [0.6375820368237944, 0.681656240341884], "95": [0.6340597504399297, 0.684351750913229]}, "precision": 0.7052631578947368, "recall": 0.6203703703703703}}}, "2020.test": {"micro/f1": 0.6475869809203142, "micro/f1_ci": {"90": [0.6267897474300171, 0.6668509760382569], "95": [0.6220217753635754, 0.6707876882456454]}, "micro/recall": 0.598858329008822, "micro/precision": 0.7049480757483201, "macro/f1": 0.6057800656625983, "macro/f1_ci": {"90": [0.5831278101058672, 0.6263507944303333], "95": [0.5785552590152583, 0.6306934757086151]}, "macro/recall": 0.5669673771050993, "macro/precision": 0.6627892226359489, "per_entity_metric": {"corporation": {"f1": 0.5618556701030927, "f1_ci": {"90": [0.49852350088248815, 0.6193234013361967], "95": [0.4861052259887006, 0.6320740777090763]}, "precision": 0.5532994923857868, "recall": 0.5706806282722513}, "creative_work": {"f1": 0.5497076023391813, "f1_ci": {"90": [0.4895030501413481, 0.6027666741522567], "95": [0.47588721221519736, 0.6109806635085506]}, "precision": 0.5766871165644172, "recall": 0.5251396648044693}, "event": {"f1": 0.4467213114754099, "f1_ci": {"90": [0.3950591617258284, 0.49787323817218776], "95": [0.3825687077007499, 0.5054575163398694]}, "precision": 0.48878923766816146, "recall": 0.41132075471698115}, "group": {"f1": 0.5316973415132924, "f1_ci": {"90": [0.4749270706399321, 0.5884958258795467], "95": [0.46389314030764484, 0.6000093808630396]}, "precision": 0.7303370786516854, "recall": 0.4180064308681672}, "location": {"f1": 0.6352941176470588, "f1_ci": {"90": [0.5737047095912183, 0.689875593176863], "95": [0.5627423945917096, 0.703535282044023]}, "precision": 0.6171428571428571, "recall": 0.6545454545454545}, "person": {"f1": 0.8364279398762157, "f1_ci": {"90": [0.8095100467932836, 0.8597686174777278], "95": [0.8044955935879107, 0.8631130405741233]}, "precision": 0.8841121495327103, "recall": 0.7936241610738255}, "product": {"f1": 0.6787564766839379, "f1_ci": {"90": [0.6229499055113231, 0.7319359334823253], "95": [0.6136336187966622, 0.739809307700981]}, "precision": 0.7891566265060241, "recall": 0.5954545454545455}}}, "2021.test (span detection)": {"micro/f1": 0.7843692816244613, "micro/f1_ci": {}, "micro/recall": 0.7683589684283566, "micro/precision": 0.8010610079575596, "macro/f1": 0.7843692816244613, "macro/f1_ci": {}, "macro/recall": 0.7683589684283566, "macro/precision": 0.8010610079575596}, "2020.test (span detection)": {"micro/f1": 0.755331088664422, "micro/f1_ci": {}, "micro/recall": 0.6984950700570836, "micro/precision": 0.8222357971899816, "macro/f1": 0.755331088664422, "macro/f1_ci": {}, "macro/recall": 0.6984950700570836, "macro/precision": 0.8222357971899816}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66882f0a17707b9e08decba98fa381683e19e0890e3a56e2c67ef8103b811318
-size 496349169
+oid sha256:02e561a94f7851b6e5fbe59c6fc91d0c06237c5fb8685715e53d22068bb669e5
+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_continuous/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": "tner/twitter-roberta-base-2019-90m-tweetner-2020", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2021.train", "model": "tner/twitter-roberta-base-2019-90m-tweetner-2020", "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": 0.3, "max_grad_norm": 1}