init
Browse files- config.json +50 -0
- parameter.json +1 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- test_bc5cdr_span_lower.json +1 -0
- test_bionlp2004_lower.json +1 -0
- test_bionlp2004_span_lower.json +1 -0
- test_conll2003_span_lower.json +1 -0
- test_fin_span_lower.json +1 -0
- test_mit_movie_trivia_span_lower.json +1 -0
- test_mit_restaurant_span_lower.json +1 -0
- test_ontonotes5_span_lower.json +1 -0
- test_panx_dataset-en_span_lower.json +1 -0
- test_wnut2017_span_lower.json +1 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-dna",
|
15 |
+
"1": "I-dna",
|
16 |
+
"2": "O",
|
17 |
+
"3": "B-protein",
|
18 |
+
"4": "I-protein",
|
19 |
+
"5": "B-cell type",
|
20 |
+
"6": "I-cell type",
|
21 |
+
"7": "B-cell line",
|
22 |
+
"8": "I-cell line",
|
23 |
+
"9": "B-rna",
|
24 |
+
"10": "I-rna"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 4096,
|
28 |
+
"label2id": {
|
29 |
+
"B-cell line": 7,
|
30 |
+
"B-cell type": 5,
|
31 |
+
"B-dna": 0,
|
32 |
+
"B-protein": 3,
|
33 |
+
"B-rna": 9,
|
34 |
+
"I-cell line": 8,
|
35 |
+
"I-cell type": 6,
|
36 |
+
"I-dna": 1,
|
37 |
+
"I-protein": 4,
|
38 |
+
"I-rna": 10,
|
39 |
+
"O": 2
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-05,
|
42 |
+
"max_position_embeddings": 514,
|
43 |
+
"model_type": "xlm-roberta",
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_hidden_layers": 24,
|
46 |
+
"output_past": true,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"vocab_size": 250002
|
50 |
+
}
|
parameter.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dataset": ["bionlp2004"], "transformers_model": "xlm-roberta-large", "random_seed": 1234, "lr": 1e-05, "total_step": 5000, "warmup_step": 700, "weight_decay": 1e-07, "batch_size": 32, "max_seq_length": 128, "fp16": false, "max_grad_norm": 1.0, "lower_case": true}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36bd60c4f66a960b1b411b0162c1ad8144e95a32514eac956f6ed404440e8a56
|
3 |
+
size 2235571258
|
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_lower.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_lower.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 74.02351156617367, "recall": 79.03748264692271, "precision": 69.60774325012736, "summary": " precision recall f1-score support\n\n cell line 0.50 0.71 0.59 500\n cell type 0.77 0.71 0.74 1920\n dna 0.67 0.76 0.71 1054\n protein 0.70 0.84 0.76 5052\n rna 0.68 0.77 0.72 118\n\n micro avg 0.70 0.79 0.74 8644\n macro avg 0.67 0.76 0.70 8644\nweighted avg 0.70 0.79 0.74 8644\n"}}
|
test_bionlp2004_span_lower.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 79.05280348394122, "recall": 84.00046274872744, "precision": 74.65556241003496, "summary": " precision recall f1-score support\n\n entity 0.75 0.84 0.79 8644\n\n micro avg 0.75 0.84 0.79 8644\n macro avg 0.75 0.84 0.79 8644\nweighted avg 0.75 0.84 0.79 8644\n"}}
|
test_conll2003_span_lower.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_fin_span_lower.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}
|
test_mit_movie_trivia_span_lower.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}
|
test_mit_restaurant_span_lower.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}
|
test_ontonotes5_span_lower.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_panx_dataset-en_span_lower.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_wnut2017_span_lower.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": ""}}
|
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-large"}
|