model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/roberta_large_continuous/best_model",
+  "_name_or_path": "tner/roberta-large-tweetner-2020",
   "adapters": {
     "adapters": {},
     "config_map": {},

eval/metric.json

@@ -1 +1 @@
-{"2021.dev": {"micro/f1": 0.6497203863751907, "micro/f1_ci": {}, "micro/recall": 0.639, "micro/precision": 0.6608066184074457, "macro/f1": 0.6040846014918451, "macro/f1_ci": {}, "macro/recall": 0.5951680223717177, "macro/precision": 0.6157020868847222, "per_entity_metric": {"corporation": {"f1": 0.5757575757575757, "f1_ci": {}, "precision": 0.59375, "recall": 0.5588235294117647}, "creative_work": {"f1": 0.5234899328859061, "f1_ci": {}, "precision": 0.52, "recall": 0.527027027027027}, "event": {"f1": 0.4201680672268908, "f1_ci": {}, "precision": 0.4672897196261682, "recall": 0.3816793893129771}, "group": {"f1": 0.627906976744186, "f1_ci": {}, "precision": 0.6650246305418719, "recall": 0.5947136563876652}, "location": {"f1": 0.6027397260273972, "f1_ci": {}, "precision": 0.5945945945945946, "recall": 0.6111111111111112}, "person": {"f1": 0.8243243243243243, "f1_ci": {}, "precision": 0.7896440129449838, "recall": 0.8621908127208481}, "product": {"f1": 0.6542056074766356, "f1_ci": {}, "precision": 0.6796116504854369, "recall": 0.6306306306306306}}}, "2021.test": {"micro/f1": 0.655251931280987, "micro/f1_ci": {"90": [0.6464329038715645, 0.6644913140065714], "95": [0.643687816840575, 0.6665911767779783]}, "micro/recall": 0.6571461609620721, "micro/precision": 0.6533685904805703, "macro/f1": 0.6038367634890193, "macro/f1_ci": {"90": [0.5943792582684101, 0.6137962439482288], "95": [0.5920045515534241, 0.6160068646604656]}, "macro/recall": 0.6086020401466904, "macro/precision": 0.6006491551013075, "per_entity_metric": {"corporation": {"f1": 0.5272331154684096, "f1_ci": {"90": [0.502525919083279, 0.5528871025664103], "95": [0.4977267887764524, 0.5575641926361611]}, "precision": 0.5170940170940171, "recall": 0.5377777777777778}, "creative_work": {"f1": 0.4389593062041361, "f1_ci": {"90": [0.4081022462482676, 0.46805875336347746], "95": [0.4031095831073842, 0.4760634486352681]}, "precision": 0.4283854166666667, "recall": 0.45006839945280436}, "event": {"f1": 0.46905222437137334, "f1_ci": {"90": [0.44597047177580085, 0.4933352272727273], "95": [0.44256911609852784, 0.4968690426958512]}, "precision": 0.500515995872033, "recall": 0.44131028207461326}, "group": {"f1": 0.6089895234876648, "f1_ci": {"90": [0.589038619038619, 0.6320534424401458], "95": [0.5849061441599553, 0.6346690132483618]}, "precision": 0.6252602359472589, "recall": 0.5935441370223979}, "location": {"f1": 0.6776099803020353, "f1_ci": {"90": [0.6494340267780017, 0.7051820267140803], "95": [0.6442522451156516, 0.7090934031674772]}, "precision": 0.6394052044609665, "recall": 0.7206703910614525}, "person": {"f1": 0.8418007593563551, "f1_ci": {"90": [0.8304729345499888, 0.8526980376362958], "95": [0.8287478255214684, 0.8544490228634517]}, "precision": 0.8258247605533877, "recall": 0.8584070796460177}, "product": {"f1": 0.6632124352331605, "f1_ci": {"90": [0.6409465020576132, 0.684911398897581], "95": [0.6370468868521454, 0.6892100086035412]}, "precision": 0.6680584551148225, "recall": 0.6584362139917695}}}, "2020.test": {"micro/f1": 0.6567328918322296, "micro/f1_ci": {"90": [0.6367329069861278, 0.6756032217463677], "95": [0.6323929424996375, 0.6804355376536286]}, "micro/recall": 0.6175402179553711, "micro/precision": 0.7012374779021803, "macro/f1": 0.6134357810007638, "macro/f1_ci": {"90": [0.5912740031546067, 0.6332647116281888], "95": [0.5881172634724844, 0.6358536607642565]}, "macro/recall": 0.57918039171165, "macro/precision": 0.6545411570113957, "per_entity_metric": {"corporation": {"f1": 0.5737265415549598, "f1_ci": {"90": [0.5165992904875836, 0.6230691426953109], "95": [0.5014568953344463, 0.6315982972136225]}, "precision": 0.5879120879120879, "recall": 0.5602094240837696}, "creative_work": {"f1": 0.49557522123893805, "f1_ci": {"90": [0.4333283877349159, 0.5505762371489373], "95": [0.4230769230769231, 0.5610579308332118]}, "precision": 0.525, "recall": 0.4692737430167598}, "event": {"f1": 0.48065173116089616, "f1_ci": {"90": [0.4288512518409425, 0.531949583718779], "95": [0.41939298355788984, 0.5424581465180373]}, "precision": 0.5221238938053098, "recall": 0.44528301886792454}, "group": {"f1": 0.5714285714285714, "f1_ci": {"90": [0.5205386474927168, 0.6214643484810444], "95": [0.5113284401613627, 0.6302839814127325]}, "precision": 0.6754385964912281, "recall": 0.49517684887459806}, "location": {"f1": 0.6461538461538462, "f1_ci": {"90": [0.5813922480620154, 0.7045138469502199], "95": [0.5730150940842019, 0.7134525767543859]}, "precision": 0.65625, "recall": 0.6363636363636364}, "person": {"f1": 0.8387096774193549, "f1_ci": {"90": [0.812278391390541, 0.8624109078217421], "95": [0.8056991909578726, 0.8681782968042391]}, "precision": 0.8729582577132486, "recall": 0.8070469798657718}, "product": {"f1": 0.6878048780487804, "f1_ci": {"90": [0.6363636363636365, 0.7363070750811945], "95": [0.6277364363130785, 0.7454572350726199]}, "precision": 0.7421052631578947, "recall": 0.6409090909090909}}}, "2021.test (span detection)": {"micro/f1": 0.7858172383972325, "micro/f1_ci": {}, "micro/recall": 0.7881346131606337, "micro/precision": 0.7835134513681306, "macro/f1": 0.7858172383972325, "macro/f1_ci": {}, "macro/recall": 0.7881346131606337, "macro/precision": 0.7835134513681306}, "2020.test (span detection)": {"micro/f1": 0.7595914987579354, "micro/f1_ci": {}, "micro/recall": 0.7140633108458744, "micro/precision": 0.8113207547169812, "macro/f1": 0.7595914987579354, "macro/f1_ci": {}, "macro/recall": 0.7140633108458744, "macro/precision": 0.8113207547169812}}
+{"2021.dev": {"micro/f1": 0.6493638676844784, "micro/f1_ci": {}, "micro/recall": 0.638, "micro/precision": 0.661139896373057, "macro/f1": 0.6064563940502387, "macro/f1_ci": {}, "macro/recall": 0.5954284242860318, "macro/precision": 0.6210253991075032, "per_entity_metric": {"corporation": {"f1": 0.5797101449275363, "f1_ci": {}, "precision": 0.5714285714285714, "recall": 0.5882352941176471}, "creative_work": {"f1": 0.4805194805194805, "f1_ci": {}, "precision": 0.4625, "recall": 0.5}, "event": {"f1": 0.4472573839662447, "f1_ci": {}, "precision": 0.5, "recall": 0.40458015267175573}, "group": {"f1": 0.6340326340326341, "f1_ci": {}, "precision": 0.6732673267326733, "recall": 0.5991189427312775}, "location": {"f1": 0.676470588235294, "f1_ci": {}, "precision": 0.71875, "recall": 0.6388888888888888}, "person": {"f1": 0.8197278911564626, "f1_ci": {}, "precision": 0.7901639344262295, "recall": 0.8515901060070671}, "product": {"f1": 0.6074766355140188, "f1_ci": {}, "precision": 0.6310679611650486, "recall": 0.5855855855855856}}}, "2021.test": {"micro/f1": 0.6602098466505246, "micro/f1_ci": {"90": [0.6517159585889167, 0.6692301926939467], "95": [0.6493037560449608, 0.6705545707079725]}, "micro/recall": 0.6621184088806661, "micro/precision": 0.6583122556909634, "macro/f1": 0.6089541397781462, "macro/f1_ci": {"90": [0.5992124192664839, 0.6181423707734851], "95": [0.5972392466243823, 0.6207098127019401]}, "macro/recall": 0.6145764579798109, "macro/precision": 0.6063426866310634, "per_entity_metric": {"corporation": {"f1": 0.5315217391304348, "f1_ci": {"90": [0.5062037953042462, 0.557002893455922], "95": [0.5029997910370321, 0.5630029363336992]}, "precision": 0.5202127659574468, "recall": 0.5433333333333333}, "creative_work": {"f1": 0.44416243654822335, "f1_ci": {"90": [0.4122197188872424, 0.47462918144124866], "95": [0.406035622185493, 0.4795]}, "precision": 0.41420118343195267, "recall": 0.478796169630643}, "event": {"f1": 0.48787728847105394, "f1_ci": {"90": [0.4644448167194252, 0.5105902072328322], "95": [0.45939395779891246, 0.5167725537147063]}, "precision": 0.53470715835141, "recall": 0.44858962693357596}, "group": {"f1": 0.6115476597198496, "f1_ci": {"90": [0.5919094922318341, 0.6339441441403232], "95": [0.5886699796091751, 0.639161660780465]}, "precision": 0.6352022711142654, "recall": 0.5895915678524374}, "location": {"f1": 0.6740692357935989, "f1_ci": {"90": [0.6463384301732925, 0.6996206891806976], "95": [0.6399452184154117, 0.704592239580396]}, "precision": 0.6331288343558282, "recall": 0.7206703910614525}, "person": {"f1": 0.8471820809248555, "f1_ci": {"90": [0.8364545587859473, 0.8578287867782268], "95": [0.8343356681910271, 0.8597832152335898]}, "precision": 0.8303824362606232, "recall": 0.8646755162241888}, "product": {"f1": 0.6663185378590079, "f1_ci": {"90": [0.6430440201857166, 0.6880601156195403], "95": [0.6389027898322917, 0.6912792458554788]}, "precision": 0.6765641569459173, "recall": 0.6563786008230452}}}, "2020.test": {"micro/f1": 0.6626406807576174, "micro/f1_ci": {"90": [0.6421811481777288, 0.6824408527817176], "95": [0.6372901150251117, 0.6854804698319146]}, "micro/recall": 0.6263622210690192, "micro/precision": 0.7033799533799534, "macro/f1": 0.6239587887403221, "macro/f1_ci": {"90": [0.602302727331785, 0.6450629596325671], "95": [0.5970260956556793, 0.6489300269035955]}, "macro/recall": 0.5921933163664825, "macro/precision": 0.6646899818440488, "per_entity_metric": {"corporation": {"f1": 0.5775401069518716, "f1_ci": {"90": [0.5159532401719902, 0.631592039800995], "95": [0.5048681813824177, 0.6443506817426007]}, "precision": 0.5901639344262295, "recall": 0.5654450261780105}, "creative_work": {"f1": 0.5414364640883977, "f1_ci": {"90": [0.48183509569087224, 0.5982905982905983], "95": [0.47114785318559554, 0.6071453442101075]}, "precision": 0.5355191256830601, "recall": 0.547486033519553}, "event": {"f1": 0.4848484848484848, "f1_ci": {"90": [0.430196666372696, 0.5392663954742951], "95": [0.41777510040160637, 0.5480195121951219]}, "precision": 0.5217391304347826, "recall": 0.4528301886792453}, "group": {"f1": 0.5752380952380952, "f1_ci": {"90": [0.5250448836936347, 0.6279727523503913], "95": [0.5077881926419612, 0.6401626025391906]}, "precision": 0.705607476635514, "recall": 0.4855305466237942}, "location": {"f1": 0.676923076923077, "f1_ci": {"90": [0.6140042598509052, 0.7335108890745321], "95": [0.6034973885094416, 0.7419877793680504]}, "precision": 0.6875, "recall": 0.6666666666666666}, "person": {"f1": 0.8333333333333334, "f1_ci": {"90": [0.8072107474406325, 0.8569065343258891], "95": [0.8017923571846364, 0.8613520685620369]}, "precision": 0.8538732394366197, "recall": 0.8137583892617449}, "product": {"f1": 0.6783919597989949, "f1_ci": {"90": [0.6273530339040599, 0.7267773646555122], "95": [0.6158022378645676, 0.7371281899611289]}, "precision": 0.7584269662921348, "recall": 0.6136363636363636}}}, "2021.test (span detection)": {"micro/f1": 0.791351974632459, "micro/f1_ci": {}, "micro/recall": 0.7936856713310975, "micro/precision": 0.78903196137043, "macro/f1": 0.791351974632459, "macro/f1_ci": {}, "macro/recall": 0.7936856713310975, "macro/precision": 0.78903196137043}, "2020.test (span detection)": {"micro/f1": 0.7644151565074135, "micro/f1_ci": {}, "micro/recall": 0.7223663725998962, "micro/precision": 0.8116618075801749, "macro/f1": 0.7644151565074135, "macro/f1_ci": {}, "macro/recall": 0.7223663725998962, "macro/precision": 0.8116618075801749}}

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>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "cner_output/model/baseline_2021/roberta_large_continuous/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>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "tner/roberta-large-tweetner-2020", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -1 +1 @@
-{"data_split": "2021.train", "model": "tner/roberta-large-tweetner-2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-06, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.15, "max_grad_norm": 1}
+{"data_split": "2021.train", "model": "tner/roberta-large-tweetner-2020", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 32, "lr": 1e-06, "random_seed": 0, "gradient_accumulation_steps": 1, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.3, "max_grad_norm": 1}