model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/self_training_2020/roberta_large/best_model",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -1 +1 @@
-{"2020.dev": {"micro/f1": 0.6474548882305414, "micro/f1_ci": {"90": [0.6251332062213224, 0.6670476285795741], "95": [0.6205911794997434, 0.67120696522025]}, "micro/recall": 0.6280041797283177, "micro/precision": 0.6681489716509171, "macro/f1": 0.5911775809856791, "macro/f1_ci": {"90": [0.5681715870342675, 0.6122873634693781], "95": [0.5640485681333156, 0.6169323276234078]}, "macro/recall": 0.5810153156344426, "macro/precision": 0.6063396515514192, "per_entity_metric": {"corporation": {"f1": 0.4831168831168831, "f1_ci": {"90": [0.4237219975462353, 0.535817575083426], "95": [0.41321427780116543, 0.5432772435897437]}, "precision": 0.510989010989011, "recall": 0.458128078817734}, "creative_work": {"f1": 0.5185185185185185, "f1_ci": {"90": [0.4568348318348318, 0.5721930646672915], "95": [0.4481858684738956, 0.5821889671361504]}, "precision": 0.5329949238578681, "recall": 0.5048076923076923}, "event": {"f1": 0.3955056179775281, "f1_ci": {"90": [0.3372904383491412, 0.45154347784144616], "95": [0.32790198679835547, 0.4629234936043549]}, "precision": 0.4656084656084656, "recall": 0.34375}, "group": {"f1": 0.5649202733485195, "f1_ci": {"90": [0.5100676577091672, 0.6154024216524216], "95": [0.4986442357498367, 0.6242171747519663]}, "precision": 0.5849056603773585, "recall": 0.5462555066079295}, "location": {"f1": 0.6565656565656566, "f1_ci": {"90": [0.5999727520435967, 0.7094007639969646], "95": [0.5914786967418546, 0.7182328994406718]}, "precision": 0.6046511627906976, "recall": 0.7182320441988951}, "person": {"f1": 0.8721934369602763, "f1_ci": {"90": [0.8487710408794229, 0.891500904159132], "95": [0.8433924577649624, 0.8951823117210236]}, "precision": 0.9017857142857143, "recall": 0.8444816053511706}, "product": {"f1": 0.6474226804123713, "f1_ci": {"90": [0.6024459556836606, 0.6881334194543706], "95": [0.5968071283726847, 0.6960387877928365]}, "precision": 0.6434426229508197, "recall": 0.6514522821576764}}}, "2021.test": {"micro/f1": 0.6462470548636822, "micro/f1_ci": {"90": [0.6372260846745648, 0.6561176673813233], "95": [0.6356931310787601, 0.65793895225239]}, "micro/recall": 0.666049953746531, "micro/precision": 0.6275877097406842, "macro/f1": 0.5928409160028406, "macro/f1_ci": {"90": [0.5834082661200564, 0.6027369680005952], "95": [0.5818688353807716, 0.605082698131854]}, "macro/recall": 0.6189640265396619, "macro/precision": 0.5724916013944144, "per_entity_metric": {"corporation": {"f1": 0.5072463768115941, "f1_ci": {"90": [0.4841311533759873, 0.5308367147024602], "95": [0.4780501760108873, 0.5353895110824435]}, "precision": 0.4748062015503876, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.4475439660400243, "f1_ci": {"90": [0.417735935143208, 0.4789241308307595], "95": [0.4129394441748634, 0.483871457986077]}, "precision": 0.4019607843137255, "recall": 0.5047879616963065}, "event": {"f1": 0.4441147378832839, "f1_ci": {"90": [0.42026714581758057, 0.4666994267703445], "95": [0.4166656358238495, 0.4719287082649152]}, "precision": 0.48645720476706394, "recall": 0.40855323020928114}, "group": {"f1": 0.6164611796067978, "f1_ci": {"90": [0.5955383856233197, 0.6392795789974397], "95": [0.5925303118049978, 0.6432657618645466]}, "precision": 0.6237356709372893, "recall": 0.6093544137022397}, "location": {"f1": 0.6525369299935774, "f1_ci": {"90": [0.6236680208089783, 0.6789095769653518], "95": [0.6183311085024601, 0.6837810101906017]}, "precision": 0.6040428061831153, "recall": 0.7094972067039106}, "person": {"f1": 0.8447562511243031, "f1_ci": {"90": [0.8347581551573588, 0.8550080856877156], "95": [0.8330373704042398, 0.857357295533503]}, "precision": 0.8247277836318933, "recall": 0.8657817109144543}, "product": {"f1": 0.6372269705603039, "f1_ci": {"90": [0.6168343256834969, 0.65883557479466], "95": [0.6118048570481955, 0.6628747232460417]}, "precision": 0.591710758377425, "recall": 0.6903292181069959}}}, "2020.test": {"micro/f1": 0.6549676025917925, "micro/f1_ci": {"90": [0.6352459708873094, 0.6732379144840148], "95": [0.6307727388454223, 0.6765402395650086]}, "micro/recall": 0.6294758692267773, "micro/precision": 0.6826111423747889, "macro/f1": 0.6138147315351224, "macro/f1_ci": {"90": [0.59154314177607, 0.632968570392166], "95": [0.5880351346026891, 0.6375830372418823]}, "macro/recall": 0.5969575608532809, "macro/precision": 0.6357805538496937, "per_entity_metric": {"corporation": {"f1": 0.5618556701030927, "f1_ci": {"90": [0.5043428993718438, 0.6161616161616161], "95": [0.4929799612152553, 0.6258776567621869]}, "precision": 0.5532994923857868, "recall": 0.5706806282722513}, "creative_work": {"f1": 0.5054945054945056, "f1_ci": {"90": [0.4477227045289312, 0.5593776914979425], "95": [0.4360349193893565, 0.5691652270109716]}, "precision": 0.4972972972972973, "recall": 0.5139664804469274}, "event": {"f1": 0.45161290322580644, "f1_ci": {"90": [0.3991120764639928, 0.5042428150331614], "95": [0.38859196675315893, 0.5133542561134965]}, "precision": 0.525, "recall": 0.39622641509433965}, "group": {"f1": 0.5842293906810035, "f1_ci": {"90": [0.5388991248272684, 0.6301894841522088], "95": [0.5320783674869244, 0.6394850127551021]}, "precision": 0.659919028340081, "recall": 0.5241157556270096}, "location": {"f1": 0.6786786786786787, "f1_ci": {"90": [0.6159137901932652, 0.7348132862943487], "95": [0.6036022709099632, 0.7437546327493262]}, "precision": 0.6726190476190477, "recall": 0.6848484848484848}, "person": {"f1": 0.8314606741573034, "f1_ci": {"90": [0.8036569096349134, 0.85612247777621], "95": [0.7982603184486745, 0.8602760969440842]}, "precision": 0.857397504456328, "recall": 0.8070469798657718}, "product": {"f1": 0.683371298405467, "f1_ci": {"90": [0.6351726068296324, 0.7309063535079794], "95": [0.6238927904522206, 0.7402053274139844]}, "precision": 0.684931506849315, "recall": 0.6818181818181818}}}, "2021.test (span detection)": {"micro/f1": 0.7861037719939289, "micro/f1_ci": {}, "micro/recall": 0.8086041401642188, "micro/precision": 0.7648217020345658, "macro/f1": 0.7861037719939289, "macro/f1_ci": {}, "macro/recall": 0.8086041401642188, "macro/precision": 0.7648217020345658}, "2020.test (span detection)": {"micro/f1": 0.7624966225344502, "micro/f1_ci": {}, "micro/recall": 0.7322262584327971, "micro/precision": 0.7953776775648252, "macro/f1": 0.7624966225344502, "macro/f1_ci": {}, "macro/recall": 0.7322262584327971, "macro/precision": 0.7953776775648252}, "2020.dev (span detection)": {"micro/f1": 0.7686084142394823, "micro/f1_ci": {}, "micro/recall": 0.7445141065830722, "micro/precision": 0.794314381270903, "macro/f1": 0.7686084142394823, "macro/f1_ci": {}, "macro/recall": 0.7445141065830722, "macro/precision": 0.794314381270903}}
+{"2020.dev": {"micro/f1": 0.6497159859345416, "micro/f1_ci": {}, "micro/recall": 0.6274817136886103, "micro/precision": 0.6735838474481212, "macro/f1": 0.595168476497736, "macro/f1_ci": {}, "macro/recall": 0.5823140804003363, "macro/precision": 0.6134127256594191, "per_entity_metric": {"corporation": {"f1": 0.503896103896104, "f1_ci": {}, "precision": 0.532967032967033, "recall": 0.47783251231527096}, "creative_work": {"f1": 0.5169082125603864, "f1_ci": {}, "precision": 0.5194174757281553, "recall": 0.5144230769230769}, "event": {"f1": 0.3747276688453159, "f1_ci": {}, "precision": 0.4236453201970443, "recall": 0.3359375}, "group": {"f1": 0.5687203791469194, "f1_ci": {}, "precision": 0.6153846153846154, "recall": 0.5286343612334802}, "location": {"f1": 0.6716417910447762, "f1_ci": {}, "precision": 0.6108597285067874, "recall": 0.7458563535911602}, "person": {"f1": 0.8765217391304349, "f1_ci": {}, "precision": 0.9130434782608695, "recall": 0.842809364548495}, "product": {"f1": 0.6537634408602151, "f1_ci": {}, "precision": 0.6785714285714286, "recall": 0.6307053941908713}}}, "2021.test": {"micro/f1": 0.6455908683974932, "micro/f1_ci": {"90": [0.6371204057050158, 0.6550747724054871], "95": [0.6350657043101348, 0.6568098006368783]}, "micro/recall": 0.6670906567992599, "micro/precision": 0.6254336513443192, "macro/f1": 0.5962839441412403, "macro/f1_ci": {"90": [0.5866402556988275, 0.6060444749938684], "95": [0.5847471469279276, 0.6077635044702457]}, "macro/recall": 0.6267698180905158, "macro/precision": 0.5727192958380657, "per_entity_metric": {"corporation": {"f1": 0.522762148337596, "f1_ci": {"90": [0.49973681393417374, 0.5471596100193149], "95": [0.4945873783946403, 0.5525733399971992]}, "precision": 0.4843601895734597, "recall": 0.5677777777777778}, "creative_work": {"f1": 0.468235294117647, "f1_ci": {"90": [0.4391420478553882, 0.4976060818012257], "95": [0.43346081582227297, 0.5044102177633336]}, "precision": 0.4107327141382869, "recall": 0.5444596443228454}, "event": {"f1": 0.4446564885496183, "f1_ci": {"90": [0.42187388657957237, 0.46923141953822195], "95": [0.4184013216599329, 0.4749416023012337]}, "precision": 0.4674022066198596, "recall": 0.4240218380345769}, "group": {"f1": 0.6155398587285571, "f1_ci": {"90": [0.5951667589966113, 0.6381605192440433], "95": [0.5920980489275562, 0.6428354803338648]}, "precision": 0.6288659793814433, "recall": 0.6027667984189723}, "location": {"f1": 0.6423718344657197, "f1_ci": {"90": [0.6144162449467848, 0.6682611851729876], "95": [0.61024506683641, 0.6720074834037416]}, "precision": 0.5758582502768549, "recall": 0.7262569832402235}, "person": {"f1": 0.840225906358171, "f1_ci": {"90": [0.8297661584761087, 0.851118291744757], "95": [0.8284000592006534, 0.8525454107688213]}, "precision": 0.8303925099027728, "recall": 0.8502949852507374}, "product": {"f1": 0.6401960784313725, "f1_ci": {"90": [0.6188782031721285, 0.6619447156064523], "95": [0.6147969820761672, 0.6654252026481837]}, "precision": 0.6114232209737828, "recall": 0.6718106995884774}}}, "2020.test": {"micro/f1": 0.6589874095901421, "micro/f1_ci": {"90": [0.6385021699858212, 0.6777882762990388], "95": [0.6344556724262541, 0.6809892848641955]}, "micro/recall": 0.6382978723404256, "micro/precision": 0.6810631229235881, "macro/f1": 0.6185133813760935, "macro/f1_ci": {"90": [0.5945654495892557, 0.6390184922948274], "95": [0.5910565487766962, 0.6431119627935548]}, "macro/recall": 0.6085669577041991, "macro/precision": 0.6351153721439261, "per_entity_metric": {"corporation": {"f1": 0.581453634085213, "f1_ci": {"90": [0.5203143050197259, 0.6341570860642527], "95": [0.5087267380681245, 0.645339211120602]}, "precision": 0.5576923076923077, "recall": 0.6073298429319371}, "creative_work": {"f1": 0.519893899204244, "f1_ci": {"90": [0.45919192076494225, 0.5729194819819821], "95": [0.4496993234778251, 0.5788147694818441]}, "precision": 0.494949494949495, "recall": 0.547486033519553}, "event": {"f1": 0.48049281314168374, "f1_ci": {"90": [0.4285569985569985, 0.5315007805396874], "95": [0.4188008130081301, 0.5401474904055986]}, "precision": 0.527027027027027, "recall": 0.44150943396226416}, "group": {"f1": 0.5724907063197026, "f1_ci": {"90": [0.5248468820106881, 0.6198803159753711], "95": [0.5152538655348761, 0.6319220978293597]}, "precision": 0.6784140969162996, "recall": 0.49517684887459806}, "location": {"f1": 0.6685878962536022, "f1_ci": {"90": [0.6005705705705706, 0.7272727272727272], "95": [0.5917728867357167, 0.7374579124579128]}, "precision": 0.6373626373626373, "recall": 0.703030303030303}, "person": {"f1": 0.8415584415584415, "f1_ci": {"90": [0.8165424697279215, 0.8626729733238138], "95": [0.8128192329092423, 0.8676861375030747]}, "precision": 0.8694096601073346, "recall": 0.8154362416107382}, "product": {"f1": 0.6651162790697673, "f1_ci": {"90": [0.6157048774126238, 0.7126683307139996], "95": [0.6045411621182, 0.723205128986824]}, "precision": 0.680952380952381, "recall": 0.65}}}, "2021.test (span detection)": {"micro/f1": 0.7846231324492194, "micro/f1_ci": {}, "micro/recall": 0.8108014340233607, "micro/precision": 0.7600823937554206, "macro/f1": 0.7846231324492194, "macro/f1_ci": {}, "macro/recall": 0.8108014340233607, "macro/precision": 0.7600823937554206}, "2020.test (span detection)": {"micro/f1": 0.7670865719646207, "micro/f1_ci": {}, "micro/recall": 0.7426050856253243, "micro/precision": 0.7932372505543237, "macro/f1": 0.7670865719646207, "macro/f1_ci": {}, "macro/recall": 0.7426050856253243, "macro/precision": 0.7932372505543237}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5472d64603abb1e3432e9d422b2195e61a42ecbd97ce4cad9ca5abe4eca96cc8
-size 1417461873
+oid sha256:94d22cb4292ef98f6d0ae4d0f29c15b99d6ea7ea8acd7b9b17e076a68c6d76e5
+size 1417467377

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, "name_or_path": "cner_output/model/self_training_2020/roberta_large/best_model", "special_tokens_map_file": "cner_output/model/self_training_2020/roberta_large/best_model/special_tokens_map.json", "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, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2020.extra.roberta-large-2020", "model": "roberta-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": 0.15, "max_grad_norm": 1}