Training in progress, step 100

.gitignore

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

config.json

@@ -0,0 +1,111 @@
+{
+  "_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-DNAMutation",
+    "4": "I-DNAMutation",
+    "5": "B-PoteinMutation",
+    "6": "I-PoteinMutation",
+    "7": "B-SNP",
+    "8": "I-SNP",
+    "9": "B-DNA_modification",
+    "10": "I-DNA_modification",
+    "11": "B-RNA",
+    "12": "I-RNA",
+    "13": "B-RNA_Mutation",
+    "14": "I-RNA_Mutation",
+    "15": "B-locus",
+    "16": "I-locus",
+    "17": "B-disease",
+    "18": "I-disease",
+    "19": "B-body-part",
+    "20": "I-body-part",
+    "21": "B-mutation",
+    "22": "I-mutation",
+    "23": "B-Physiology",
+    "24": "I-Physiology",
+    "25": "B-cohort-patient",
+    "26": "I-cohort-patient",
+    "27": "B-size",
+    "28": "I-size",
+    "29": "B-gender",
+    "30": "I-gender",
+    "31": "B-age",
+    "32": "I-age",
+    "33": "B-Concepts_Ideas",
+    "34": "I-Concepts_Ideas",
+    "35": "B-Disorder",
+    "36": "I-Disorder",
+    "37": "B-Phenomena",
+    "38": "I-Phenomena",
+    "39": "B-ethnicity",
+    "40": "I-ethnicity"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Concepts_Ideas": 33,
+    "B-DNAMutation": 3,
+    "B-DNA_modification": 9,
+    "B-Disorder": 35,
+    "B-Gene_Protein": 1,
+    "B-Phenomena": 37,
+    "B-Physiology": 23,
+    "B-PoteinMutation": 5,
+    "B-RNA": 11,
+    "B-RNA_Mutation": 13,
+    "B-SNP": 7,
+    "B-age": 31,
+    "B-body-part": 19,
+    "B-cohort-patient": 25,
+    "B-disease": 17,
+    "B-ethnicity": 39,
+    "B-gender": 29,
+    "B-locus": 15,
+    "B-mutation": 21,
+    "B-size": 27,
+    "I-Concepts_Ideas": 34,
+    "I-DNAMutation": 4,
+    "I-DNA_modification": 10,
+    "I-Disorder": 36,
+    "I-Gene_Protein": 2,
+    "I-Phenomena": 38,
+    "I-Physiology": 24,
+    "I-PoteinMutation": 6,
+    "I-RNA": 12,
+    "I-RNA_Mutation": 14,
+    "I-SNP": 8,
+    "I-age": 32,
+    "I-body-part": 20,
+    "I-cohort-patient": 26,
+    "I-disease": 18,
+    "I-ethnicity": 40,
+    "I-gender": 30,
+    "I-locus": 16,
+    "I-mutation": 22,
+    "I-size": 28,
+    "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 sha256:6638fd7fb348bee137b5416cd19ef267fd8edafd0488b0a0c94b8af752588a1b
+size 435764845

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 sha256:7069ac9bf62fff3696887965e55623ed297174a735be731395003508686fe0d3
+size 3579