model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/baseline_2021/roberta_base_concat/best_model",
+  "_name_or_path": "roberta-base",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"2021.dev": {"micro/f1": 0.6469689251146206, "micro/f1_ci": {}, "micro/recall": 0.635, "micro/precision": 0.6593977154724818, "macro/f1": 0.6014288931166422, "macro/f1_ci": {}, "macro/recall": 0.5903596479194196, "macro/precision": 0.6143183232533814, "per_entity_metric": {"corporation": {"f1": 0.6019417475728156, "f1_ci": {}, "precision": 0.5961538461538461, "recall": 0.6078431372549019}, "creative_work": {"f1": 0.47887323943661975, "f1_ci": {}, "precision": 0.5, "recall": 0.4594594594594595}, "event": {"f1": 0.41767068273092367, "f1_ci": {}, "precision": 0.4406779661016949, "recall": 0.3969465648854962}, "group": {"f1": 0.631578947368421, "f1_ci": {}, "precision": 0.62882096069869, "recall": 0.6343612334801763}, "location": {"f1": 0.6122448979591836, "f1_ci": {}, "precision": 0.6, "recall": 0.625}, "person": {"f1": 0.8366247755834828, "f1_ci": {}, "precision": 0.8503649635036497, "recall": 0.823321554770318}, "product": {"f1": 0.6310679611650485, "f1_ci": {}, "precision": 0.6842105263157895, "recall": 0.5855855855855856}}}, "2021.test": {"micro/f1": 0.6515831894070236, "micro/f1_ci": {"90": [0.6426248846161623, 0.6611146727643068], "95": [0.6408583849998567, 0.6629609445072536]}, "micro/recall": 0.6543709528214616, "micro/precision": 0.6488190781930749, "macro/f1": 0.6081318073591985, "macro/f1_ci": {"90": [0.5982720247328263, 0.6181304060646944], "95": [0.5956407088917159, 0.6196130125852912]}, "macro/recall": 0.6155807376978756, "macro/precision": 0.6024892144112918, "per_entity_metric": {"corporation": {"f1": 0.5174234424498415, "f1_ci": {"90": [0.4936648515870705, 0.5437348601262041], "95": [0.4885022949243286, 0.5471504446094865]}, "precision": 0.49295774647887325, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.466403162055336, "f1_ci": {"90": [0.4365426214916792, 0.49570670195121297], "95": [0.430553631074086, 0.5016692736109198]}, "precision": 0.4498094027954257, "recall": 0.4842681258549932}, "event": {"f1": 0.46727272727272723, "f1_ci": {"90": [0.4454429687968715, 0.4903171853702863], "95": [0.44099256614662297, 0.4949513525562855]}, "precision": 0.46684831970935514, "recall": 0.467697907188353}, "group": {"f1": 0.6071197411003236, "f1_ci": {"90": [0.5861576908243826, 0.6289925904123155], "95": [0.5836863413397794, 0.6323354921624595]}, "precision": 0.5966921119592875, "recall": 0.6179183135704874}, "location": {"f1": 0.6832786885245901, "f1_ci": {"90": [0.6571720974465681, 0.7109068486625629], "95": [0.6508663190665896, 0.7162931067002565]}, "precision": 0.6440049443757726, "recall": 0.7276536312849162}, "person": {"f1": 0.8377301195672804, "f1_ci": {"90": [0.8276980959235751, 0.8485767478830628], "95": [0.8260255921110556, 0.8508092332281014]}, "precision": 0.8631208447399296, "recall": 0.8137905604719764}, "product": {"f1": 0.6776947705442904, "f1_ci": {"90": [0.6553902251490492, 0.699632094409221], "95": [0.6517642249373523, 0.7046841960928648]}, "precision": 0.7039911308203991, "recall": 0.6532921810699589}}}, "2020.test": {"micro/f1": 0.6531839300355288, "micro/f1_ci": {"90": [0.6331939425228015, 0.6709196392454311], "95": [0.6287463050212823, 0.6742363307437226]}, "micro/recall": 0.6201349247535028, "micro/precision": 0.6899538106235565, "macro/f1": 0.6166186507300974, "macro/f1_ci": {"90": [0.594157548648219, 0.6362144855158252], "95": [0.5904501135575192, 0.639776197480569]}, "macro/recall": 0.5860926262979317, "macro/precision": 0.6523781324413148, "per_entity_metric": {"corporation": {"f1": 0.6194225721784777, "f1_ci": {"90": [0.5565017746228926, 0.6733323349589473], "95": [0.5479085471734517, 0.6820512820512821]}, "precision": 0.6210526315789474, "recall": 0.6178010471204188}, "creative_work": {"f1": 0.4894259818731118, "f1_ci": {"90": [0.4270354135925701, 0.545507399577167], "95": [0.41717142698274423, 0.5555627705627706]}, "precision": 0.5328947368421053, "recall": 0.45251396648044695}, "event": {"f1": 0.45136186770428016, "f1_ci": {"90": [0.3978736734522443, 0.501874083251449], "95": [0.3891742854740079, 0.510803537621031]}, "precision": 0.46586345381526106, "recall": 0.4377358490566038}, "group": {"f1": 0.5658362989323844, "f1_ci": {"90": [0.5151382476251127, 0.61462698148764], "95": [0.5076307180164151, 0.626772526987192]}, "precision": 0.6334661354581673, "recall": 0.5112540192926045}, "location": {"f1": 0.6894409937888198, "f1_ci": {"90": [0.6274217149546386, 0.7440886398547689], "95": [0.6148768819473758, 0.7561225667461723]}, "precision": 0.7070063694267515, "recall": 0.6727272727272727}, "person": {"f1": 0.8275261324041812, "f1_ci": {"90": [0.7993567425754086, 0.8511074607796776], "95": [0.7958273985244123, 0.8545669887000585]}, "precision": 0.8605072463768116, "recall": 0.7969798657718121}, "product": {"f1": 0.6733167082294264, "f1_ci": {"90": [0.6190924641557551, 0.723014061091403], "95": [0.6093323046153235, 0.7345134333722708]}, "precision": 0.7458563535911602, "recall": 0.6136363636363636}}}, "2021.test (span detection)": {"micro/f1": 0.7893373251194657, "micro/f1_ci": {}, "micro/recall": 0.7927604949693535, "micro/precision": 0.7859435909195138, "macro/f1": 0.7893373251194657, "macro/f1_ci": {}, "macro/recall": 0.7927604949693535, "macro/precision": 0.7859435909195138}, "2020.test (span detection)": {"micro/f1": 0.7523236741388737, "micro/f1_ci": {}, "micro/recall": 0.7140633108458744, "micro/precision": 0.7949162333911034, "macro/f1": 0.7523236741388737, "macro/f1_ci": {}, "macro/recall": 0.7140633108458744, "macro/precision": 0.7949162333911034}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c978a4b32d1bc36c9d574ad02191a8c0a7da65b8256636b99a81dc2a98d907
-size 496349169
+oid sha256:254fdb2ce80df08cd7d5f31a8c90353de05c8312ebcea89b419dd7ecdbad8574
+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, "name_or_path": "cner_output/model/baseline_2021/roberta_base_concat/best_model", "special_tokens_map_file": "cner_output/model/baseline_2021/roberta_base_concat/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-base", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "2020_2021.train", "model": "roberta-base", "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}