init
Browse files- config.json +54 -0
- parameter.json +1 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- test_bc5cdr_span.json +1 -0
- test_bionlp2004_span.json +1 -0
- test_conll2003_span.json +1 -0
- test_fin_span.json +1 -0
- test_ontonotes5_span.json +1 -0
- test_panx_dataset-en_span.json +1 -0
- test_wnut2017.json +1 -0
- test_wnut2017_span.json +1 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-location",
|
16 |
+
"2": "I-location",
|
17 |
+
"3": "B-group",
|
18 |
+
"4": "B-corporation",
|
19 |
+
"5": "B-person",
|
20 |
+
"6": "B-work of art",
|
21 |
+
"7": "B-product",
|
22 |
+
"8": "I-person",
|
23 |
+
"9": "I-work of art",
|
24 |
+
"10": "I-corporation",
|
25 |
+
"11": "I-group",
|
26 |
+
"12": "I-product"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"label2id": {
|
31 |
+
"B-corporation": 4,
|
32 |
+
"B-group": 3,
|
33 |
+
"B-location": 1,
|
34 |
+
"B-person": 5,
|
35 |
+
"B-product": 7,
|
36 |
+
"B-work of art": 6,
|
37 |
+
"I-corporation": 10,
|
38 |
+
"I-group": 11,
|
39 |
+
"I-location": 2,
|
40 |
+
"I-person": 8,
|
41 |
+
"I-product": 12,
|
42 |
+
"I-work of art": 9,
|
43 |
+
"O": 0
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"max_position_embeddings": 514,
|
47 |
+
"model_type": "xlm-roberta",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_hidden_layers": 12,
|
50 |
+
"output_past": true,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"type_vocab_size": 1,
|
53 |
+
"vocab_size": 250002
|
54 |
+
}
|
parameter.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dataset": ["wnut2017"], "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 sha256:456f1656e7e629890ce5838dd4f13092a758cc77086283c4c0933fe1420979cf
|
3 |
+
size 1109937680
|
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": 83.91780821917808, "recall": 83.64281813216822, "precision": 84.19461242440902, "summary": " precision recall f1-score support\n\n entity 0.84 0.84 0.84 3662\n\n micro avg 0.84 0.84 0.84 3662\n macro avg 0.84 0.84 0.84 3662\nweighted avg 0.84 0.84 0.84 3662\n"}, "test": {"f1": 81.24999999999999, "recall": 81.89602446483181, "precision": 80.61408789885611, "summary": " precision recall f1-score support\n\n entity 0.81 0.82 0.81 3270\n\n micro avg 0.81 0.82 0.81 3270\n macro avg 0.81 0.82 0.81 3270\nweighted avg 0.81 0.82 0.81 3270\n"}}
|
test_fin_span.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 20.51282051282051, "recall": 13.861386138613863, "precision": 39.436619718309856, "summary": " precision recall f1-score support\n\n entity 0.39 0.14 0.21 202\n\n micro avg 0.39 0.14 0.21 202\n macro avg 0.39 0.14 0.21 202\nweighted avg 0.39 0.14 0.21 202\n"}}
|
test_ontonotes5_span.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 39.880188275566965, "recall": 56.84659957304056, "precision": 30.713461855330365, "summary": " precision recall f1-score support\n\n entity 0.31 0.57 0.40 3279\n\n micro avg 0.31 0.57 0.40 3279\n macro avg 0.31 0.57 0.40 3279\nweighted avg 0.31 0.57 0.40 3279\n"}, "test": {"f1": 41.320320210549404, "recall": 57.969230769230776, "precision": 32.10086897256773, "summary": " precision recall f1-score support\n\n entity 0.32 0.58 0.41 3250\n\n micro avg 0.32 0.58 0.41 3250\n macro avg 0.32 0.58 0.41 3250\nweighted avg 0.32 0.58 0.41 3250\n"}}
|
test_panx_dataset-en_span.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 56.800000000000004, "recall": 63.943632125450314, "precision": 51.092109718929905, "summary": " precision recall f1-score support\n\n entity 0.51 0.64 0.57 9438\n\n micro avg 0.51 0.64 0.57 9438\n macro avg 0.51 0.64 0.57 9438\nweighted avg 0.51 0.64 0.57 9438\n"}, "test": {"f1": 56.25512616394075, "recall": 63.71584699453552, "precision": 50.35846937894101, "summary": " precision recall f1-score support\n\n entity 0.50 0.64 0.56 9150\n\n micro avg 0.50 0.64 0.56 9150\n macro avg 0.50 0.64 0.56 9150\nweighted avg 0.50 0.64 0.56 9150\n"}}
|
test_wnut2017.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 62.81879194630873, "recall": 55.980861244019145, "precision": 71.55963302752293, "summary": " precision recall f1-score support\n\n corporation 0.43 0.38 0.41 34\n group 0.25 0.26 0.25 39\n location 0.66 0.61 0.63 74\n person 0.86 0.71 0.77 470\n product 0.59 0.36 0.45 114\n work of art 0.46 0.26 0.33 105\n\n micro avg 0.72 0.56 0.63 836\n macro avg 0.54 0.43 0.47 836\nweighted avg 0.71 0.56 0.62 836\n"}, "test": {"f1": 52.844638949671776, "recall": 44.84679665738162, "precision": 64.31424766977364, "summary": " precision recall f1-score support\n\n corporation 0.33 0.32 0.33 66\n group 0.48 0.28 0.35 165\n location 0.67 0.58 0.62 150\n person 0.81 0.62 0.70 428\n product 0.33 0.17 0.23 127\n work of art 0.61 0.30 0.41 141\n\n micro avg 0.64 0.45 0.53 1077\n macro avg 0.54 0.38 0.44 1077\nweighted avg 0.63 0.45 0.52 1077\n"}}
|
test_wnut2017_span.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 73.03295225285811, "recall": 64.95215311004785, "precision": 83.41013824884793, "summary": " precision recall f1-score support\n\n entity 0.83 0.65 0.73 836\n\n micro avg 0.83 0.65 0.73 836\n macro avg 0.83 0.65 0.73 836\nweighted avg 0.83 0.65 0.73 836\n"}, "test": {"f1": 63.00164925783397, "recall": 53.2033426183844, "precision": 77.22371967654986, "summary": " precision recall f1-score support\n\n entity 0.77 0.53 0.63 1077\n\n micro avg 0.77 0.53 0.63 1077\n macro avg 0.77 0.53 0.63 1077\nweighted avg 0.77 0.53 0.63 1077\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"}
|