Training in progress, step 100

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Gene_protein",
+    "2": "I-Gene_protein",
+    "3": "B-DNA_Mutation",
+    "4": "I-DNA_Mutation",
+    "5": "B-DNA_modification",
+    "6": "I-DNA_modification",
+    "7": "B-locus",
+    "8": "I-locus",
+    "9": "B-Mutation",
+    "10": "I-Mutation",
+    "11": "B-dbSNP",
+    "12": "I-dbSNP",
+    "13": "B-Protein_Mutation",
+    "14": "I-Protein_Mutation",
+    "15": "B-RNA",
+    "16": "I-RNA",
+    "17": "B-RNA_Mutation",
+    "18": "I-RNA_Mutation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DNA_Mutation": 3,
+    "B-DNA_modification": 5,
+    "B-Gene_protein": 1,
+    "B-Mutation": 9,
+    "B-Protein_Mutation": 13,
+    "B-RNA": 15,
+    "B-RNA_Mutation": 17,
+    "B-dbSNP": 11,
+    "B-locus": 7,
+    "I-DNA_Mutation": 4,
+    "I-DNA_modification": 6,
+    "I-Gene_protein": 2,
+    "I-Mutation": 10,
+    "I-Protein_Mutation": 14,
+    "I-RNA": 16,
+    "I-RNA_Mutation": 18,
+    "I-dbSNP": 12,
+    "I-locus": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e23f837f093e9d50af8dedeaefbfaf1c76ca216e30505942ba564e37d2c984
+size 435697197

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_len": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "trunction": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bde6402f97b178b91c7d3452a993506dd8f2a1615c76578506149cb05980c3e
+size 3579