model update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "cner_output/model/random_split/t_roberta_base_dec2020/best_model",
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-dec2020",
   "architectures": [
     "RobertaForTokenClassification"
   ],

eval/metric.json

@@ -0,0 +1 @@
+{"random.dev": {"micro/f1": 0.636139292569235, "micro/f1_ci": {}, "micro/recall": 0.6193272824345969, "micro/precision": 0.6538895152198422, "macro/f1": 0.5889505868453838, "macro/f1_ci": {}, "macro/recall": 0.5747770006058855, "macro/precision": 0.6048487753165137, "per_entity_metric": {"corporation": {"f1": 0.5054945054945055, "f1_ci": {}, "precision": 0.5380116959064327, "recall": 0.47668393782383417}, "creative_work": {"f1": 0.4921135646687697, "f1_ci": {}, "precision": 0.5032258064516129, "recall": 0.48148148148148145}, "event": {"f1": 0.3678646934460888, "f1_ci": {}, "precision": 0.3815789473684211, "recall": 0.3551020408163265}, "group": {"f1": 0.6110283159463488, "f1_ci": {}, "precision": 0.6307692307692307, "recall": 0.5924855491329479}, "location": {"f1": 0.6686567164179105, "f1_ci": {}, "precision": 0.6511627906976745, "recall": 0.6871165644171779}, "person": {"f1": 0.8582302568981922, "f1_ci": {}, "precision": 0.8706563706563707, "recall": 0.8461538461538461}, "product": {"f1": 0.6192660550458715, "f1_ci": {}, "precision": 0.6585365853658537, "recall": 0.5844155844155844}}}, "2021.test": {"micro/f1": 0.647180429539451, "micro/f1_ci": {"90": [0.638863290259823, 0.6571232166113093], "95": [0.6369059711235887, 0.6583232503306811]}, "micro/recall": 0.651595744680851, "micro/precision": 0.6428245493953912, "macro/f1": 0.599724784991918, "macro/f1_ci": {"90": [0.5898083141176582, 0.6102417714069138], "95": [0.5883541467624883, 0.6118892806343514]}, "macro/recall": 0.6075992592680901, "macro/precision": 0.5927116702269455, "per_entity_metric": {"corporation": {"f1": 0.49081803005008345, "f1_ci": {"90": [0.4659487770408919, 0.5182997799087251], "95": [0.4607175510034198, 0.5226749309775297]}, "precision": 0.4916387959866221, "recall": 0.49}, "creative_work": {"f1": 0.4642392717815344, "f1_ci": {"90": [0.43437985968912063, 0.49609799842004704], "95": [0.4293175625975742, 0.50293712081692]}, "precision": 0.4423791821561338, "recall": 0.4883720930232558}, "event": {"f1": 0.4564920273348519, "f1_ci": {"90": [0.43312040607394414, 0.4805105894941198], "95": [0.4290331073815886, 0.48513216306524937]}, "precision": 0.45711678832116787, "recall": 0.45586897179253866}, "group": {"f1": 0.6168039538714991, "f1_ci": {"90": [0.596835997433537, 0.6375918997219351], "95": [0.5930045786258692, 0.6423742481136104]}, "precision": 0.6170072511535926, "recall": 0.616600790513834}, "location": {"f1": 0.6750496360026472, "f1_ci": {"90": [0.6483953111117986, 0.7020357363811676], "95": [0.6442174340711808, 0.7062758926474242]}, "precision": 0.6415094339622641, "recall": 0.7122905027932961}, "person": {"f1": 0.8331479421579534, "f1_ci": {"90": [0.8224552661031729, 0.8444571403179274], "95": [0.8204713825881407, 0.8460376396156104]}, "precision": 0.8378076062639821, "recall": 0.8285398230088495}, "product": {"f1": 0.661522633744856, "f1_ci": {"90": [0.6407822659293477, 0.6827506165675322], "95": [0.6355335831565007, 0.6869551952078615]}, "precision": 0.661522633744856, "recall": 0.661522633744856}}}, "2020.test": {"micro/f1": 0.6469310157523085, "micro/f1_ci": {"90": [0.6255332972787668, 0.6659736408494877], "95": [0.6224135756691761, 0.6702426848338685]}, "micro/recall": 0.6180591593149974, "micro/precision": 0.6786324786324787, "macro/f1": 0.6053228739595288, "macro/f1_ci": {"90": [0.5811485400719889, 0.625587676346971], "95": [0.5779351962830672, 0.630439252296093]}, "macro/recall": 0.5799081543030431, "macro/precision": 0.6353958642029116, "per_entity_metric": {"corporation": {"f1": 0.5555555555555557, "f1_ci": {"90": [0.49450244200244203, 0.6116561964591661], "95": [0.4842493589606233, 0.6220230556337368]}, "precision": 0.5614973262032086, "recall": 0.5497382198952879}, "creative_work": {"f1": 0.5384615384615384, "f1_ci": {"90": [0.479163765088208, 0.5944598315516683], "95": [0.4689400972590627, 0.6025773195876288]}, "precision": 0.5723270440251572, "recall": 0.5083798882681564}, "event": {"f1": 0.44274809160305345, "f1_ci": {"90": [0.3905637631216805, 0.4928571428571428], "95": [0.38058704004728827, 0.5038339866584143]}, "precision": 0.44787644787644787, "recall": 0.4377358490566038}, "group": {"f1": 0.5656934306569343, "f1_ci": {"90": [0.5115089837170129, 0.6180623574777951], "95": [0.49914021378118173, 0.626345170668137]}, "precision": 0.6540084388185654, "recall": 0.4983922829581994}, "location": {"f1": 0.6504559270516718, "f1_ci": {"90": [0.5806338822467855, 0.711697116442879], "95": [0.5667472773335965, 0.7247410144283611]}, "precision": 0.6524390243902439, "recall": 0.6484848484848484}, "person": {"f1": 0.8402777777777778, "f1_ci": {"90": [0.8144796380090498, 0.8632005454395977], "95": [0.810303182503082, 0.8675224547771234]}, "precision": 0.8705035971223022, "recall": 0.8120805369127517}, "product": {"f1": 0.6440677966101694, "f1_ci": {"90": [0.587443946188341, 0.6988570255688482], "95": [0.5747000587297592, 0.7104135562854583]}, "precision": 0.689119170984456, "recall": 0.6045454545454545}}}, "2021.test (span detection)": {"micro/f1": 0.7828633779360248, "micro/f1_ci": {}, "micro/recall": 0.7882502602058518, "micro/precision": 0.7775496235455168, "macro/f1": 0.7828633779360248, "macro/f1_ci": {}, "macro/recall": 0.7882502602058518, "macro/precision": 0.7775496235455168}, "2020.test (span detection)": {"micro/f1": 0.7593699076588811, "micro/f1_ci": {}, "micro/recall": 0.7254800207576544, "micro/precision": 0.7965811965811965, "macro/f1": 0.7593699076588811, "macro/f1_ci": {}, "macro/recall": 0.7254800207576544, "macro/precision": 0.7965811965811965}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cd87b595ed3b9ccf6d66870cf43e476ca507734bdc1ce44936178e2d34aba0
-size 496349169
+oid sha256:bf591c074d33be03aec4c93da70b2a4b7f20dd8b58a6b2acde68c5d839402158
+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/random_split/t_roberta_base_dec2020/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": "cardiffnlp/twitter-roberta-base-dec2020", "tokenizer_class": "RobertaTokenizer"}

trainer_config.json

@@ -0,0 +1 @@
+{"data_split": "random.train", "model": "cardiffnlp/twitter-roberta-base-dec2020", "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}