model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline/bertweet_large/best_model",
+  "_name_or_path": "vinai/bertweet-large",
   "adapters": {
     "adapters": {},
     "config_map": {},

eval/metric.json

@@ -1 +1 @@
-{"2020.dev": {"micro/f1": 0.646448087431694, "micro/f1_ci": {"90": [0.6231243785105754, 0.6657449692607822], "95": [0.6186646533471, 0.6692250307072554]}, "micro/recall": 0.6180773249738767, "micro/precision": 0.6775486827033219, "macro/f1": 0.5897644786894204, "macro/f1_ci": {"90": [0.5660692755411003, 0.6105223675662451], "95": [0.5604760622008684, 0.6144388896475745]}, "macro/recall": 0.5664383777167729, "macro/precision": 0.6180566669308823, "per_entity_metric": {"corporation": {"f1": 0.5000000000000001, "f1_ci": {"90": [0.4396455894853854, 0.5550909090909091], "95": [0.4298494632852927, 0.565524968608133]}, "precision": 0.5575757575757576, "recall": 0.45320197044334976}, "creative_work": {"f1": 0.5330073349633252, "f1_ci": {"90": [0.47500000000000003, 0.5865118387557972], "95": [0.45855196148029265, 0.5961576517150395]}, "precision": 0.5422885572139303, "recall": 0.5240384615384616}, "event": {"f1": 0.39490445859872614, "f1_ci": {"90": [0.34116833830306315, 0.44861266874350986], "95": [0.3295546401135254, 0.45874770642201845]}, "precision": 0.4325581395348837, "recall": 0.36328125}, "group": {"f1": 0.5599999999999999, "f1_ci": {"90": [0.4955628153171781, 0.6120590628996628], "95": [0.4833824269889225, 0.6213613477512694]}, "precision": 0.601010101010101, "recall": 0.5242290748898678}, "location": {"f1": 0.6246719160104987, "f1_ci": {"90": [0.56633358006415, 0.6816729314795525], "95": [0.5509541275884482, 0.6892798876098976]}, "precision": 0.595, "recall": 0.6574585635359116}, "person": {"f1": 0.8773747841105354, "f1_ci": {"90": [0.8554281650045316, 0.8960138648180243], "95": [0.8516878481256623, 0.9016447797538809]}, "precision": 0.9071428571428571, "recall": 0.8494983277591973}, "product": {"f1": 0.6383928571428571, "f1_ci": {"90": [0.5904677994545836, 0.6851503483681702], "95": [0.5789181286549707, 0.6926886883042058]}, "precision": 0.6908212560386473, "recall": 0.5933609958506224}}}, "2021.test": {"micro/f1": 0.6398329005306537, "micro/f1_ci": {"90": [0.6307204094450275, 0.6495242037413694], "95": [0.6287932101355881, 0.6506176608713055]}, "micro/recall": 0.6552960222016652, "micro/precision": 0.6250827266710788, "macro/f1": 0.5925342242253508, "macro/f1_ci": {"90": [0.5825493957674438, 0.6018753104051382], "95": [0.5806714217780672, 0.6041867778989004]}, "macro/recall": 0.6127398470143047, "macro/precision": 0.5760695685532945, "per_entity_metric": {"corporation": {"f1": 0.5005107252298262, "f1_ci": {"90": [0.4753333754112458, 0.5265897982203284], "95": [0.47012239027524416, 0.5319285700037899]}, "precision": 0.46313799621928164, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.4612476370510397, "f1_ci": {"90": [0.4285577711007921, 0.49289342880956877], "95": [0.42247452788081197, 0.49761433721744336]}, "precision": 0.42757009345794394, "recall": 0.5006839945280438}, "event": {"f1": 0.4647191011235955, "f1_ci": {"90": [0.44280892366715674, 0.48591833932745304], "95": [0.4381962048712117, 0.49149062829852297]}, "precision": 0.4591474245115453, "recall": 0.47042766151046406}, "group": {"f1": 0.5946684894053315, "f1_ci": {"90": [0.573699478600635, 0.6173373969706688], "95": [0.5704640172875658, 0.6207669609843738]}, "precision": 0.6178977272727273, "recall": 0.5731225296442688}, "location": {"f1": 0.6523115896136794, "f1_ci": {"90": [0.6248328887216571, 0.67925342577298], "95": [0.6175339060649391, 0.6849731420051927]}, "precision": 0.59675550405562, "recall": 0.7192737430167597}, "person": {"f1": 0.8301613195577306, "f1_ci": {"90": [0.8195963536640386, 0.8403641923923699], "95": [0.8173660585609337, 0.8427281912413296]}, "precision": 0.8163992869875223, "recall": 0.8443952802359882}, "product": {"f1": 0.6441207075962538, "f1_ci": {"90": [0.621830027895911, 0.6652983657627619], "95": [0.617194844930694, 0.6695352680970291]}, "precision": 0.651578947368421, "recall": 0.6368312757201646}}}, "2020.test": {"micro/f1": 0.6606948968512487, "micro/f1_ci": {"90": [0.6396078627506032, 0.6798592856407392], "95": [0.6359905597872999, 0.6831830655326773]}, "micro/recall": 0.6315516346652829, "micro/precision": 0.6926579396698919, "macro/f1": 0.6245930396980819, "macro/f1_ci": {"90": [0.6022566771903995, 0.646224996738906], "95": [0.5968409364130149, 0.6506271665344884]}, "macro/recall": 0.6041674527775335, "macro/precision": 0.6541947337729395, "per_entity_metric": {"corporation": {"f1": 0.5944584382871535, "f1_ci": {"90": [0.5359624682205327, 0.6500123152709361], "95": [0.5242666528217642, 0.6599508816120907]}, "precision": 0.5728155339805825, "recall": 0.6178010471204188}, "creative_work": {"f1": 0.5619834710743802, "f1_ci": {"90": [0.5, 0.6201599450495535], "95": [0.4924796454208219, 0.6284156412248069]}, "precision": 0.5543478260869565, "recall": 0.5698324022346368}, "event": {"f1": 0.46758349705304514, "f1_ci": {"90": [0.4161825165985544, 0.5158638015949801], "95": [0.40579416174265803, 0.5275280389132383]}, "precision": 0.48770491803278687, "recall": 0.4490566037735849}, "group": {"f1": 0.5877862595419847, "f1_ci": {"90": [0.5344537815126051, 0.6415915646682778], "95": [0.5213844935331696, 0.6505577704745316]}, "precision": 0.7230046948356808, "recall": 0.49517684887459806}, "location": {"f1": 0.6686046511627907, "f1_ci": {"90": [0.6019387040813221, 0.7262498810049242], "95": [0.5939756726329357, 0.7365348250866688]}, "precision": 0.6424581005586593, "recall": 0.696969696969697}, "person": {"f1": 0.8317349607672189, "f1_ci": {"90": [0.8045460633464769, 0.8544826361906804], "95": [0.7981426309729419, 0.86027322696934]}, "precision": 0.8656987295825771, "recall": 0.8003355704697986}, "product": {"f1": 0.6599999999999999, "f1_ci": {"90": [0.6069562367801709, 0.7103963829019999], "95": [0.5947368421052632, 0.7204036997914465]}, "precision": 0.7333333333333333, "recall": 0.6}}}, "2021.test (span detection)": {"micro/f1": 0.7799920962005308, "micro/f1_ci": {}, "micro/recall": 0.7988897883659073, "micro/precision": 0.7619677917493933, "macro/f1": 0.7799920962005308, "macro/f1_ci": {}, "macro/recall": 0.7988897883659073, "macro/precision": 0.7619677917493933}, "2020.test (span detection)": {"micro/f1": 0.7691472026072786, "micro/f1_ci": {}, "micro/recall": 0.7348209652309289, "micro/precision": 0.8068376068376069, "macro/f1": 0.7691472026072786, "macro/f1_ci": {}, "macro/recall": 0.7348209652309289, "macro/precision": 0.8068376068376069}, "2020.dev (span detection)": {"micro/f1": 0.7628415300546447, "micro/f1_ci": {}, "micro/recall": 0.7293625914315569, "micro/precision": 0.7995418098510882, "macro/f1": 0.7628415300546447, "macro/f1_ci": {}, "macro/recall": 0.7293625914315569, "macro/precision": 0.7995418098510882}}
+{"2020.dev": {"micro/f1": 0.6437029063509151, "micro/f1_ci": {}, "micro/recall": 0.6248693834900731, "micro/precision": 0.6637069922308546, "macro/f1": 0.591642865243014, "macro/f1_ci": {}, "macro/recall": 0.5755700410698614, "macro/precision": 0.6133965500147562, "per_entity_metric": {"corporation": {"f1": 0.5051546391752577, "f1_ci": {}, "precision": 0.5297297297297298, "recall": 0.4827586206896552}, "creative_work": {"f1": 0.54, "f1_ci": {}, "precision": 0.5625, "recall": 0.5192307692307693}, "event": {"f1": 0.39312977099236646, "f1_ci": {}, "precision": 0.3843283582089552, "recall": 0.40234375}, "group": {"f1": 0.5495049504950495, "f1_ci": {}, "precision": 0.6271186440677966, "recall": 0.4889867841409692}, "location": {"f1": 0.6227848101265823, "f1_ci": {}, "precision": 0.5747663551401869, "recall": 0.6795580110497238}, "person": {"f1": 0.874675885911841, "f1_ci": {}, "precision": 0.9051878354203936, "recall": 0.8461538461538461}, "product": {"f1": 0.6562500000000001, "f1_ci": {}, "precision": 0.7101449275362319, "recall": 0.6099585062240664}}}, "2021.test": {"micro/f1": 0.6401254269555967, "micro/f1_ci": {"90": [0.6315544728348781, 0.6491758274095626], "95": [0.6294268706225905, 0.6515448119225267]}, "micro/recall": 0.6609620721554117, "micro/precision": 0.6205623710780589, "macro/f1": 0.5947383155381057, "macro/f1_ci": {"90": [0.5852724504065837, 0.6043623226898465], "95": [0.5836410112124547, 0.6063768583335745]}, "macro/recall": 0.6206178838164583, "macro/precision": 0.5738855505495571, "per_entity_metric": {"corporation": {"f1": 0.5229357798165137, "f1_ci": {"90": [0.49706039551042225, 0.5489060654201801], "95": [0.49299356150347506, 0.5543603424996233]}, "precision": 0.4830508474576271, "recall": 0.57}, "creative_work": {"f1": 0.4629981024667932, "f1_ci": {"90": [0.43277573053403184, 0.4925610964986595], "95": [0.4272513399167463, 0.49761378932009187]}, "precision": 0.43058823529411766, "recall": 0.5006839945280438}, "event": {"f1": 0.4499572284003422, "f1_ci": {"90": [0.4274287289095753, 0.47154022208242086], "95": [0.4228081863105448, 0.47623473640595676]}, "precision": 0.4245359160613398, "recall": 0.4786169244767971}, "group": {"f1": 0.592749032030975, "f1_ci": {"90": [0.5722540581576642, 0.6147130977130977], "95": [0.5676533946830992, 0.6194597542880659]}, "precision": 0.636432350718065, "recall": 0.5546772068511199}, "location": {"f1": 0.6553030303030303, "f1_ci": {"90": [0.6304163397345088, 0.6817280494561573], "95": [0.6255962515548817, 0.6867043413492904]}, "precision": 0.597926267281106, "recall": 0.7248603351955307}, "person": {"f1": 0.8273135669362084, "f1_ci": {"90": [0.8160811561878993, 0.8380472862595445], "95": [0.814691063129817, 0.8397603550670991]}, "precision": 0.806869961444094, "recall": 0.8488200589970502}, "product": {"f1": 0.6519114688128772, "f1_ci": {"90": [0.6299024970087858, 0.6725193990424303], "95": [0.6268028691225062, 0.6764233561966475]}, "precision": 0.6377952755905512, "recall": 0.6666666666666666}}}, "2020.test": {"micro/f1": 0.659346545259775, "micro/f1_ci": {"90": [0.638530476656731, 0.6770002736609395], "95": [0.6355787571672109, 0.6814383304317009]}, "micro/recall": 0.6388168137000519, "micro/precision": 0.6812396236856668, "macro/f1": 0.6261309560026784, "macro/f1_ci": {"90": [0.6035614787399021, 0.6466837937863731], "95": [0.6008212526260872, 0.6498051149764593]}, "macro/recall": 0.6111694484964181, "macro/precision": 0.6527657911787169, "per_entity_metric": {"corporation": {"f1": 0.5966587112171838, "f1_ci": {"90": [0.5434307846076962, 0.6461646550171141], "95": [0.5326863869413766, 0.6552623249971564]}, "precision": 0.5482456140350878, "recall": 0.6544502617801047}, "creative_work": {"f1": 0.5892351274787537, "f1_ci": {"90": [0.5297221164826799, 0.6412325295653509], "95": [0.5167939021229471, 0.6498711140898077]}, "precision": 0.5977011494252874, "recall": 0.5810055865921788}, "event": {"f1": 0.4500907441016334, "f1_ci": {"90": [0.4, 0.5], "95": [0.3933869964988056, 0.5071014607812004]}, "precision": 0.43356643356643354, "recall": 0.4679245283018868}, "group": {"f1": 0.5454545454545454, "f1_ci": {"90": [0.4908707249478041, 0.5995649027168184], "95": [0.47806491874824353, 0.6098095911901321]}, "precision": 0.7076923076923077, "recall": 0.4437299035369775}, "location": {"f1": 0.6808510638297872, "f1_ci": {"90": [0.6158357771260997, 0.7378894784375705], "95": [0.6056659605996418, 0.7468373964681981]}, "precision": 0.6829268292682927, "recall": 0.6787878787878788}, "person": {"f1": 0.8358974358974359, "f1_ci": {"90": [0.8090079967608057, 0.8589565954118873], "95": [0.802661820512157, 0.864705203631851]}, "precision": 0.8519163763066202, "recall": 0.8204697986577181}, "product": {"f1": 0.6847290640394088, "f1_ci": {"90": [0.6328984758460346, 0.731190820093083], "95": [0.6213509150900847, 0.7403650506863269]}, "precision": 0.7473118279569892, "recall": 0.6318181818181818}}}, "2021.test (span detection)": {"micro/f1": 0.7826184343151529, "micro/f1_ci": {}, "micro/recall": 0.8081415519833468, "micro/precision": 0.7586581261535121, "macro/f1": 0.7826184343151529, "macro/f1_ci": {}, "macro/recall": 0.8081415519833468, "macro/precision": 0.7586581261535121}, "2020.test (span detection)": {"micro/f1": 0.7738478027867096, "micro/f1_ci": {}, "micro/recall": 0.749351323300467, "micro/precision": 0.8, "macro/f1": 0.7738478027867096, "macro/f1_ci": {}, "macro/recall": 0.749351323300467, "macro/precision": 0.8}}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "cner_output/model/baseline/bertweet_large/best_model", "tokenizer_class": "RobertaTokenizer"}
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "vinai/bertweet-large", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

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