model update
Browse files- config.json +1 -1
- eval/metric.json +1 -1
- eval/prediction.2020.dev.json +0 -0
- eval/prediction.2020.test.json +0 -0
- eval/prediction.2021.test.json +0 -0
- pytorch_model.bin +2 -2
- tokenizer.json +2 -4
- tokenizer_config.json +1 -2
- trainer_config.json +1 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaForTokenClassification"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
"architectures": [
|
4 |
"RobertaForTokenClassification"
|
5 |
],
|
eval/metric.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"2020.dev": {"micro/f1": 0.
|
|
|
1 |
+
{"2020.dev": {"micro/f1": 0.6461038961038961, "micro/f1_ci": {}, "micro/recall": 0.6238244514106583, "micro/precision": 0.67003367003367, "macro/f1": 0.587322338466695, "macro/f1_ci": {}, "macro/recall": 0.5756381956969621, "macro/precision": 0.6090469200966296, "per_entity_metric": {"corporation": {"f1": 0.484375, "f1_ci": {}, "precision": 0.5138121546961326, "recall": 0.458128078817734}, "creative_work": {"f1": 0.511520737327189, "f1_ci": {}, "precision": 0.4911504424778761, "recall": 0.5336538461538461}, "event": {"f1": 0.38613861386138615, "f1_ci": {}, "precision": 0.527027027027027, "recall": 0.3046875}, "group": {"f1": 0.5733333333333334, "f1_ci": {}, "precision": 0.57847533632287, "recall": 0.5682819383259912}, "location": {"f1": 0.640625, "f1_ci": {}, "precision": 0.6059113300492611, "recall": 0.6795580110497238}, "person": {"f1": 0.8709122203098106, "f1_ci": {}, "precision": 0.8971631205673759, "recall": 0.8461538461538461}, "product": {"f1": 0.6443514644351463, "f1_ci": {}, "precision": 0.6497890295358649, "recall": 0.6390041493775933}}}, "2021.test": {"micro/f1": 0.6451758087201125, "micro/f1_ci": {"90": [0.6360452531843157, 0.6546242674951402], "95": [0.6344128889037165, 0.6562435584441533]}, "micro/recall": 0.6630434782608695, "micro/precision": 0.6282458639202366, "macro/f1": 0.5945137835095485, "macro/f1_ci": {"90": [0.5849625646474219, 0.6048099476423717], "95": [0.5832263131312113, 0.6064180014512437]}, "macro/recall": 0.6195808065595296, "macro/precision": 0.5791991181065553, "per_entity_metric": {"corporation": {"f1": 0.5067218200620476, "f1_ci": {"90": [0.482720115378613, 0.5318353967881462], "95": [0.4796950147983722, 0.5369819879159188]}, "precision": 0.4738878143133462, "recall": 0.5444444444444444}, "creative_work": {"f1": 0.45376220562894887, "f1_ci": {"90": [0.42664800694587557, 0.48082929944314123], "95": [0.42158048043728424, 0.4846494398622172]}, "precision": 0.3910891089108911, "recall": 0.5403556771545828}, "event": {"f1": 0.4452749599572877, "f1_ci": {"90": [0.41903187721369545, 0.4705294264916067], "95": [0.41504947523868935, 0.4746242629321899]}, "precision": 0.5387596899224806, "recall": 0.3794358507734304}, "group": {"f1": 0.6063348416289593, "f1_ci": {"90": [0.5861107400130976, 0.6279132370043825], "95": [0.5830224656689539, 0.6322202313625416]}, "precision": 0.5951776649746193, "recall": 0.6179183135704874}, "location": {"f1": 0.6619263089851325, "f1_ci": {"90": [0.6324935407210904, 0.6882328863476124], "95": [0.6253949479866915, 0.6927306998069366]}, "precision": 0.6161251504211793, "recall": 0.7150837988826816}, "person": {"f1": 0.835890955046037, "f1_ci": {"90": [0.8259559078534311, 0.8463653140397381], "95": [0.8236693872632049, 0.848508779376511]}, "precision": 0.8188892819243013, "recall": 0.8536135693215339}, "product": {"f1": 0.651685393258427, "f1_ci": {"90": [0.6290720140515222, 0.6729078211863003], "95": [0.6251710926532523, 0.6767235821801794]}, "precision": 0.6204651162790698, "recall": 0.6862139917695473}}}, "2020.test": {"micro/f1": 0.6605206073752712, "micro/f1_ci": {"90": [0.6408255159753993, 0.6793274637933173], "95": [0.6373893291997992, 0.6825239933971441]}, "micro/recall": 0.6320705760249092, "micro/precision": 0.6916524701873935, "macro/f1": 0.6182768841282975, "macro/f1_ci": {"90": [0.5961031178968297, 0.6385985065596177], "95": [0.5914673366772406, 0.6421666965178469]}, "macro/recall": 0.600022393469146, "macro/precision": 0.646958757311601, "per_entity_metric": {"corporation": {"f1": 0.5822784810126582, "f1_ci": {"90": [0.5256752905886762, 0.6318421628123121], "95": [0.5128, 0.6414092076062835]}, "precision": 0.5637254901960784, "recall": 0.6020942408376964}, "creative_work": {"f1": 0.5343915343915344, "f1_ci": {"90": [0.476412981770012, 0.588596538853071], "95": [0.4636852685629959, 0.5979764281221802]}, "precision": 0.507537688442211, "recall": 0.5642458100558659}, "event": {"f1": 0.4439252336448598, "f1_ci": {"90": [0.38862436460968, 0.497920986683701], "95": [0.3779821592181615, 0.5074727486164683]}, "precision": 0.5828220858895705, "recall": 0.3584905660377358}, "group": {"f1": 0.597864768683274, "f1_ci": {"90": [0.5551718002208861, 0.6446087202184763], "95": [0.548585759887216, 0.6524932368209403]}, "precision": 0.6693227091633466, "recall": 0.5401929260450161}, "location": {"f1": 0.6808510638297872, "f1_ci": {"90": [0.6142731829573934, 0.743047103899031], "95": [0.6024013007045483, 0.7507189002768739]}, "precision": 0.6829268292682927, "recall": 0.6787878787878788}, "person": {"f1": 0.8343347639484978, "f1_ci": {"90": [0.8076569065611846, 0.8573930598247411], "95": [0.8034319572294566, 0.8639877286061661]}, "precision": 0.8541300527240774, "recall": 0.8154362416107382}, "product": {"f1": 0.6542923433874709, "f1_ci": {"90": [0.6053549332303825, 0.7005813660209848], "95": [0.5979308671922375, 0.7089777612241414]}, "precision": 0.6682464454976303, "recall": 0.6409090909090909}}}, "2021.test (span detection)": {"micro/f1": 0.7849668054461573, "micro/f1_ci": {}, "micro/recall": 0.8067537874407309, "micro/precision": 0.7643256272597787, "macro/f1": 0.7849668054461573, "macro/f1_ci": {}, "macro/recall": 0.8067537874407309, "macro/precision": 0.7643256272597787}, "2020.test (span detection)": {"micro/f1": 0.769397721106891, "micro/f1_ci": {}, "micro/recall": 0.7358588479501816, "micro/precision": 0.8061398521887436, "macro/f1": 0.769397721106891, "macro/f1_ci": {}, "macro/recall": 0.7358588479501816, "macro/precision": 0.8061398521887436}}
|
eval/prediction.2020.dev.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
eval/prediction.2020.test.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
eval/prediction.2021.test.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30c08fba6e00561b8cdcde41eb9a80fb82bc92b3f49fd455e5260f2402b0f19d
|
3 |
+
size 1417438577
|
tokenizer.json
CHANGED
@@ -53,8 +53,7 @@
|
|
53 |
"pre_tokenizer": {
|
54 |
"type": "ByteLevel",
|
55 |
"add_prefix_space": false,
|
56 |
-
"trim_offsets": true
|
57 |
-
"use_regex": true
|
58 |
},
|
59 |
"post_processor": {
|
60 |
"type": "RobertaProcessing",
|
@@ -72,8 +71,7 @@
|
|
72 |
"decoder": {
|
73 |
"type": "ByteLevel",
|
74 |
"add_prefix_space": true,
|
75 |
-
"trim_offsets": true
|
76 |
-
"use_regex": true
|
77 |
},
|
78 |
"model": {
|
79 |
"type": "BPE",
|
|
|
53 |
"pre_tokenizer": {
|
54 |
"type": "ByteLevel",
|
55 |
"add_prefix_space": false,
|
56 |
+
"trim_offsets": true
|
|
|
57 |
},
|
58 |
"post_processor": {
|
59 |
"type": "RobertaProcessing",
|
|
|
71 |
"decoder": {
|
72 |
"type": "ByteLevel",
|
73 |
"add_prefix_space": true,
|
74 |
+
"trim_offsets": true
|
|
|
75 |
},
|
76 |
"model": {
|
77 |
"type": "BPE",
|
tokenizer_config.json
CHANGED
@@ -6,10 +6,9 @@
|
|
6 |
"errors": "replace",
|
7 |
"mask_token": "<mask>",
|
8 |
"model_max_length": 512,
|
9 |
-
"name_or_path": "
|
10 |
"pad_token": "<pad>",
|
11 |
"sep_token": "</s>",
|
12 |
-
"special_tokens_map_file": "cner_output/model/self_training_2021/roberta_large_concat/best_model/special_tokens_map.json",
|
13 |
"tokenizer_class": "RobertaTokenizer",
|
14 |
"trim_offsets": true,
|
15 |
"unk_token": "<unk>"
|
|
|
6 |
"errors": "replace",
|
7 |
"mask_token": "<mask>",
|
8 |
"model_max_length": 512,
|
9 |
+
"name_or_path": "roberta-large",
|
10 |
"pad_token": "<pad>",
|
11 |
"sep_token": "</s>",
|
|
|
12 |
"tokenizer_class": "RobertaTokenizer",
|
13 |
"trim_offsets": true,
|
14 |
"unk_token": "<unk>"
|
trainer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"data_split": "2020_2021.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": 0.3, "max_grad_norm": 1}
|