init

config.json

@@ -0,0 +1,38 @@
+{
+  "_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-chemical",
+    "1": "O",
+    "2": "B-disease",
+    "3": "I-disease",
+    "4": "I-chemical"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-chemical": 0,
+    "B-disease": 2,
+    "I-chemical": 4,
+    "I-disease": 3,
+    "O": 1
+  },
+  "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": ["bc5cdr"], "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 sha256:522145dcbede32701a95e6bc20238614f9948532dc2774d597a999b0c99300e2
+size 2235549102

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.json

@@ -0,0 +1 @@
+{"valid": {"f1": 89.5432629996371, "recall": 90.44826141600335, "precision": 88.65619546247818, "accuracy": 97.77135896347427, "summary": "              precision    recall  f1-score   support\n\n    chemical       0.93      0.94      0.94      5324\n     disease       0.83      0.86      0.85      4224\n\n   micro avg       0.89      0.90      0.90      9548\n   macro avg       0.88      0.90      0.89      9548\nweighted avg       0.89      0.90      0.90      9548\n"}, "test": {"f1": 88.65504109039888, "recall": 90.35750766087844, "precision": 87.01554200275427, "accuracy": 97.64993014471256, "summary": "              precision    recall  f1-score   support\n\n    chemical       0.92      0.94      0.93      5374\n     disease       0.81      0.86      0.83      4416\n\n   micro avg       0.87      0.90      0.89      9790\n   macro avg       0.87      0.90      0.88      9790\nweighted avg       0.87      0.90      0.89      9790\n"}}

test_bc5cdr_span.json

@@ -0,0 +1 @@
+{"valid": {"f1": 89.82153973853497, "recall": 90.66820276497695, "precision": 88.9905427631579, "accuracy": 97.82119193075063, "summary": "              precision    recall  f1-score   support\n\n      entity       0.89      0.91      0.90      9548\n\n   micro avg       0.89      0.91      0.90      9548\n   macro avg       0.89      0.91      0.90      9548\nweighted avg       0.89      0.91      0.90      9548\n"}, "test": {"f1": 88.87663542032183, "recall": 90.55158324821247, "precision": 87.2625258391574, "accuracy": 97.69736274729635, "summary": "              precision    recall  f1-score   support\n\n      entity       0.87      0.91      0.89      9790\n\n   micro avg       0.87      0.91      0.89      9790\n   macro avg       0.87      0.91      0.89      9790\nweighted avg       0.87      0.91      0.89      9790\n"}}

test_bionlp2004_span.json

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

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"}