init

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "B-dna",
+    "1": "I-dna",
+    "2": "O",
+    "3": "B-protein",
+    "4": "I-protein",
+    "5": "B-cell type",
+    "6": "I-cell type",
+    "7": "B-cell line",
+    "8": "I-cell line",
+    "9": "B-rna",
+    "10": "I-rna"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-cell line": 7,
+    "B-cell type": 5,
+    "B-dna": 0,
+    "B-protein": 3,
+    "B-rna": 9,
+    "I-cell line": 8,
+    "I-cell type": 6,
+    "I-dna": 1,
+    "I-protein": 4,
+    "I-rna": 10,
+    "O": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 250002
+}

parameter.json

@@ -0,0 +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": false}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b504f4f12d325aa70da7f10d98457165126f0c2271b7d245459f8626188d1929
+size 2235573781

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +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

@@ -0,0 +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.json

@@ -0,0 +1 @@
+{"valid": {"f1": 74.37587809359127, "recall": 79.6251301631378, "precision": 69.77593024434756, "accuracy": 94.07436826689172, "summary": "              precision    recall  f1-score   support\n\n   cell line       0.52      0.72      0.60       500\n   cell type       0.76      0.71      0.73      1919\n         dna       0.68      0.76      0.71      1054\n     protein       0.71      0.85      0.77      5052\n         rna       0.67      0.75      0.71       118\n\n   micro avg       0.70      0.80      0.74      8643\n   macro avg       0.67      0.76      0.71      8643\nweighted avg       0.70      0.80      0.74      8643\n"}}

test_bionlp2004_span.json

@@ -0,0 +1 @@
+{"valid": {"f1": 79.04425739885963, "recall": 84.20687261367581, "precision": 74.47810069586573, "accuracy": 95.17251650697513, "summary": "              precision    recall  f1-score   support\n\n      entity       0.74      0.84      0.79      8643\n\n   micro avg       0.74      0.84      0.79      8643\n   macro avg       0.74      0.84      0.79      8643\nweighted avg       0.74      0.84      0.79      8643\n"}}

test_conll2003_span.json

@@ -0,0 +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.json

@@ -0,0 +1 @@
+{"valid": {"f1": 0.0, "recall": 0.0, "precision": 0.0, "summary": ""}}

test_ontonotes5_span.json

@@ -0,0 +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.json

@@ -0,0 +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.json

@@ -0,0 +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

@@ -0,0 +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"}