asahi417 commited on
Commit
70a4a78
1 Parent(s): 4a71449
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-cardinal number",
16
+ "2": "B-date",
17
+ "3": "I-date",
18
+ "4": "B-person",
19
+ "5": "I-person",
20
+ "6": "B-group",
21
+ "7": "B-geopolitical area",
22
+ "8": "I-geopolitical area",
23
+ "9": "B-law",
24
+ "10": "I-law",
25
+ "11": "B-organization",
26
+ "12": "I-organization",
27
+ "13": "B-percent",
28
+ "14": "I-percent",
29
+ "15": "B-ordinal number",
30
+ "16": "B-money",
31
+ "17": "I-money",
32
+ "18": "B-work of art",
33
+ "19": "I-work of art",
34
+ "20": "B-facility",
35
+ "21": "B-time",
36
+ "22": "I-cardinal number",
37
+ "23": "B-location",
38
+ "24": "B-quantity",
39
+ "25": "I-quantity",
40
+ "26": "I-group",
41
+ "27": "I-location",
42
+ "28": "B-product",
43
+ "29": "I-time",
44
+ "30": "B-event",
45
+ "31": "I-event",
46
+ "32": "I-facility",
47
+ "33": "B-language",
48
+ "34": "I-product",
49
+ "35": "I-ordinal number",
50
+ "36": "I-language"
51
+ },
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 3072,
54
+ "label2id": {
55
+ "B-cardinal number": 1,
56
+ "B-date": 2,
57
+ "B-event": 30,
58
+ "B-facility": 20,
59
+ "B-geopolitical area": 7,
60
+ "B-group": 6,
61
+ "B-language": 33,
62
+ "B-law": 9,
63
+ "B-location": 23,
64
+ "B-money": 16,
65
+ "B-ordinal number": 15,
66
+ "B-organization": 11,
67
+ "B-percent": 13,
68
+ "B-person": 4,
69
+ "B-product": 28,
70
+ "B-quantity": 24,
71
+ "B-time": 21,
72
+ "B-work of art": 18,
73
+ "I-cardinal number": 22,
74
+ "I-date": 3,
75
+ "I-event": 31,
76
+ "I-facility": 32,
77
+ "I-geopolitical area": 8,
78
+ "I-group": 26,
79
+ "I-language": 36,
80
+ "I-law": 10,
81
+ "I-location": 27,
82
+ "I-money": 17,
83
+ "I-ordinal number": 35,
84
+ "I-organization": 12,
85
+ "I-percent": 14,
86
+ "I-person": 5,
87
+ "I-product": 34,
88
+ "I-quantity": 25,
89
+ "I-time": 29,
90
+ "I-work of art": 19,
91
+ "O": 0
92
+ },
93
+ "layer_norm_eps": 1e-05,
94
+ "max_position_embeddings": 514,
95
+ "model_type": "xlm-roberta",
96
+ "num_attention_heads": 12,
97
+ "num_hidden_layers": 12,
98
+ "output_past": true,
99
+ "pad_token_id": 1,
100
+ "type_vocab_size": 1,
101
+ "vocab_size": 250002
102
+ }
parameter.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dataset": ["ontonotes5"], "transformers_model": "xlm-roberta-base", "random_seed": 1234, "lr": 1e-05, "total_step": 13000, "warmup_step": 700, "weight_decay": 1e-07, "batch_size": 16, "max_seq_length": 128, "fp16": false, "max_grad_norm": 1.0, "lower_case": false}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c17f9d9b4742ac5aa7f0e56886c3b4fef04737f67efb63730616a17cf39682
3
+ size 1110011650
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
test_bc5cdr_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}, "test": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}
test_bionlp2004_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}
test_conll2003_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 64.09021794221997, "recall": 50.54967019788127, "precision": 87.53894080996885, "summary": " precision recall f1-score support\n\n entity 0.88 0.51 0.64 5003\n\n micro avg 0.88 0.51 0.64 5003\n macro avg 0.88 0.51 0.64 5003\nweighted avg 0.88 0.51 0.64 5003\n"}, "test": {"f1": 62.21701795472286, "recall": 48.48915027377814, "precision": 86.78765880217786, "summary": " precision recall f1-score support\n\n entity 0.87 0.48 0.62 4931\n\n micro avg 0.87 0.48 0.62 4931\n macro avg 0.87 0.48 0.62 4931\nweighted avg 0.87 0.48 0.62 4931\n"}}
test_fin_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 31.753554502369667, "recall": 26.58730158730159, "precision": 39.411764705882355, "summary": " precision recall f1-score support\n\n entity 0.39 0.27 0.32 252\n\n micro avg 0.39 0.27 0.32 252\n macro avg 0.39 0.27 0.32 252\nweighted avg 0.39 0.27 0.32 252\n"}}
test_ontonotes5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 86.98359051896652, "recall": 88.57893306765692, "precision": 85.4446968373231, "summary": " precision recall f1-score support\n\n cardinal number 0.82 0.88 0.85 937\n date 0.83 0.87 0.85 1507\n event 0.63 0.55 0.59 143\n facility 0.54 0.64 0.59 115\ngeopolitical area 0.94 0.93 0.94 2262\n group 0.90 0.93 0.91 847\n language 0.86 0.73 0.79 33\n law 0.46 0.70 0.55 40\n location 0.67 0.74 0.70 204\n money 0.90 0.93 0.92 274\n ordinal number 0.83 0.86 0.85 232\n organization 0.86 0.86 0.86 1728\n percent 0.89 0.89 0.89 177\n person 0.91 0.96 0.93 2014\n product 0.55 0.67 0.60 72\n quantity 0.79 0.81 0.80 100\n time 0.68 0.79 0.73 214\n work of art 0.42 0.54 0.48 142\n\n micro avg 0.85 0.89 0.87 11041\n macro avg 0.75 0.79 0.77 11041\n weighted avg 0.86 0.89 0.87 11041\n"}, "test": {"f1": 89.0153671030165, "recall": 90.35641276330992, "precision": 87.71354616048318, "summary": " precision recall f1-score support\n\n cardinal number 0.85 0.88 0.86 934\n date 0.84 0.89 0.86 1601\n event 0.61 0.65 0.63 63\n facility 0.76 0.74 0.75 135\ngeopolitical area 0.96 0.96 0.96 2240\n group 0.89 0.94 0.92 841\n language 0.75 0.55 0.63 22\n law 0.63 0.60 0.62 40\n location 0.70 0.80 0.74 179\n money 0.85 0.90 0.87 314\n ordinal number 0.81 0.92 0.86 195\n organization 0.89 0.89 0.89 1792\n percent 0.89 0.92 0.90 348\n person 0.93 0.96 0.95 1988\n product 0.65 0.72 0.69 76\n quantity 0.77 0.81 0.79 105\n time 0.60 0.66 0.63 212\n work of art 0.60 0.60 0.60 166\n\n micro avg 0.88 0.90 0.89 11251\n macro avg 0.78 0.80 0.79 11251\n weighted avg 0.88 0.90 0.89 11251\n"}}
test_ontonotes5_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 91.05923313841896, "recall": 92.38293632823114, "precision": 89.77292730153142, "summary": " precision recall f1-score support\n\n entity 0.90 0.92 0.91 11041\n\n micro avg 0.90 0.92 0.91 11041\n macro avg 0.90 0.92 0.91 11041\nweighted avg 0.90 0.92 0.91 11041\n"}, "test": {"f1": 91.83754116355654, "recall": 92.95173762332237, "precision": 90.7497396737244, "summary": " precision recall f1-score support\n\n entity 0.91 0.93 0.92 11251\n\n micro avg 0.91 0.93 0.92 11251\n macro avg 0.91 0.93 0.92 11251\nweighted avg 0.91 0.93 0.92 11251\n"}}
test_panx_dataset-en_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 44.32529043789097, "recall": 35.13992206872122, "precision": 60.01209921355112, "summary": " precision recall f1-score support\n\n entity 0.60 0.35 0.44 14115\n\n micro avg 0.60 0.35 0.44 14115\n macro avg 0.60 0.35 0.44 14115\nweighted avg 0.60 0.35 0.44 14115\n"}, "test": {"f1": 44.73243010557796, "recall": 35.526126385490144, "precision": 60.379204892966364, "summary": " precision recall f1-score support\n\n entity 0.60 0.36 0.45 13894\n\n micro avg 0.60 0.36 0.45 13894\n macro avg 0.60 0.36 0.45 13894\nweighted avg 0.60 0.36 0.45 13894\n"}}
test_wnut2017_span.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"valid": {"f1": 62.40928882438316, "recall": 53.61596009975062, "precision": 74.65277777777779, "summary": " precision recall f1-score support\n\n entity 0.75 0.54 0.62 802\n\n micro avg 0.75 0.54 0.62 802\n macro avg 0.75 0.54 0.62 802\nweighted avg 0.75 0.54 0.62 802\n"}, "test": {"f1": 51.70387779083432, "recall": 43.52126607319486, "precision": 63.67583212735166, "summary": " precision recall f1-score support\n\n entity 0.64 0.44 0.52 1011\n\n micro avg 0.64 0.44 0.52 1011\n macro avg 0.64 0.44 0.52 1011\nweighted avg 0.64 0.44 0.52 1011\n"}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "xlm-roberta-base"}