Model save

README.md

@@ -0,0 +1,48 @@
+---
+license: mit
+base_model: Clinical-AI-Apollo/Medical-NER
+tags:
+- generated_from_trainer
+model-index:
+- name: Medical-NER-finetuned-ner
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Medical-NER-finetuned-ner
+
+This model is a fine-tuned version of [Clinical-AI-Apollo/Medical-NER](https://huggingface.co/Clinical-AI-Apollo/Medical-NER) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 6
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 1.12.1+cu102
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,205 @@
+{
+  "_name_or_path": "Clinical-AI-Apollo/Medical-NER",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ACTIVITY",
+    "2": "I-ACTIVITY",
+    "3": "I-ADMINISTRATION",
+    "4": "B-ADMINISTRATION",
+    "5": "B-AGE",
+    "6": "I-AGE",
+    "7": "I-AREA",
+    "8": "B-AREA",
+    "9": "B-BIOLOGICAL_ATTRIBUTE",
+    "10": "I-BIOLOGICAL_ATTRIBUTE",
+    "11": "I-BIOLOGICAL_STRUCTURE",
+    "12": "B-BIOLOGICAL_STRUCTURE",
+    "13": "B-CLINICAL_EVENT",
+    "14": "I-CLINICAL_EVENT",
+    "15": "B-COLOR",
+    "16": "I-COLOR",
+    "17": "I-COREFERENCE",
+    "18": "B-COREFERENCE",
+    "19": "B-DATE",
+    "20": "I-DATE",
+    "21": "I-DETAILED_DESCRIPTION",
+    "22": "B-DETAILED_DESCRIPTION",
+    "23": "I-DIAGNOSTIC_PROCEDURE",
+    "24": "B-DIAGNOSTIC_PROCEDURE",
+    "25": "I-DISEASE_DISORDER",
+    "26": "B-DISEASE_DISORDER",
+    "27": "B-DISTANCE",
+    "28": "I-DISTANCE",
+    "29": "B-DOSAGE",
+    "30": "I-DOSAGE",
+    "31": "I-DURATION",
+    "32": "B-DURATION",
+    "33": "I-FAMILY_HISTORY",
+    "34": "B-FAMILY_HISTORY",
+    "35": "B-FREQUENCY",
+    "36": "I-FREQUENCY",
+    "37": "I-HEIGHT",
+    "38": "B-HEIGHT",
+    "39": "B-HISTORY",
+    "40": "I-HISTORY",
+    "41": "I-LAB_VALUE",
+    "42": "B-LAB_VALUE",
+    "43": "I-MASS",
+    "44": "B-MASS",
+    "45": "I-MEDICATION",
+    "46": "B-MEDICATION",
+    "47": "I-NONBIOLOGICAL_LOCATION",
+    "48": "B-NONBIOLOGICAL_LOCATION",
+    "49": "I-OCCUPATION",
+    "50": "B-OCCUPATION",
+    "51": "B-OTHER_ENTITY",
+    "52": "I-OTHER_ENTITY",
+    "53": "B-OTHER_EVENT",
+    "54": "I-OTHER_EVENT",
+    "55": "I-OUTCOME",
+    "56": "B-OUTCOME",
+    "57": "I-PERSONAL_BACKGROUND",
+    "58": "B-PERSONAL_BACKGROUND",
+    "59": "B-QUALITATIVE_CONCEPT",
+    "60": "I-QUALITATIVE_CONCEPT",
+    "61": "I-QUANTITATIVE_CONCEPT",
+    "62": "B-QUANTITATIVE_CONCEPT",
+    "63": "B-SEVERITY",
+    "64": "I-SEVERITY",
+    "65": "B-SEX",
+    "66": "I-SEX",
+    "67": "B-SHAPE",
+    "68": "I-SHAPE",
+    "69": "B-SIGN_SYMPTOM",
+    "70": "I-SIGN_SYMPTOM",
+    "71": "B-SUBJECT",
+    "72": "I-SUBJECT",
+    "73": "B-TEXTURE",
+    "74": "I-TEXTURE",
+    "75": "B-THERAPEUTIC_PROCEDURE",
+    "76": "I-THERAPEUTIC_PROCEDURE",
+    "77": "I-TIME",
+    "78": "B-TIME",
+    "79": "B-VOLUME",
+    "80": "I-VOLUME",
+    "81": "I-WEIGHT",
+    "82": "B-WEIGHT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACTIVITY": 1,
+    "B-ADMINISTRATION": 4,
+    "B-AGE": 5,
+    "B-AREA": 8,
+    "B-BIOLOGICAL_ATTRIBUTE": 9,
+    "B-BIOLOGICAL_STRUCTURE": 12,
+    "B-CLINICAL_EVENT": 13,
+    "B-COLOR": 15,
+    "B-COREFERENCE": 18,
+    "B-DATE": 19,
+    "B-DETAILED_DESCRIPTION": 22,
+    "B-DIAGNOSTIC_PROCEDURE": 24,
+    "B-DISEASE_DISORDER": 26,
+    "B-DISTANCE": 27,
+    "B-DOSAGE": 29,
+    "B-DURATION": 32,
+    "B-FAMILY_HISTORY": 34,
+    "B-FREQUENCY": 35,
+    "B-HEIGHT": 38,
+    "B-HISTORY": 39,
+    "B-LAB_VALUE": 42,
+    "B-MASS": 44,
+    "B-MEDICATION": 46,
+    "B-NONBIOLOGICAL_LOCATION": 48,
+    "B-OCCUPATION": 50,
+    "B-OTHER_ENTITY": 51,
+    "B-OTHER_EVENT": 53,
+    "B-OUTCOME": 56,
+    "B-PERSONAL_BACKGROUND": 58,
+    "B-QUALITATIVE_CONCEPT": 59,
+    "B-QUANTITATIVE_CONCEPT": 62,
+    "B-SEVERITY": 63,
+    "B-SEX": 65,
+    "B-SHAPE": 67,
+    "B-SIGN_SYMPTOM": 69,
+    "B-SUBJECT": 71,
+    "B-TEXTURE": 73,
+    "B-THERAPEUTIC_PROCEDURE": 75,
+    "B-TIME": 78,
+    "B-VOLUME": 79,
+    "B-WEIGHT": 82,
+    "I-ACTIVITY": 2,
+    "I-ADMINISTRATION": 3,
+    "I-AGE": 6,
+    "I-AREA": 7,
+    "I-BIOLOGICAL_ATTRIBUTE": 10,
+    "I-BIOLOGICAL_STRUCTURE": 11,
+    "I-CLINICAL_EVENT": 14,
+    "I-COLOR": 16,
+    "I-COREFERENCE": 17,
+    "I-DATE": 20,
+    "I-DETAILED_DESCRIPTION": 21,
+    "I-DIAGNOSTIC_PROCEDURE": 23,
+    "I-DISEASE_DISORDER": 25,
+    "I-DISTANCE": 28,
+    "I-DOSAGE": 30,
+    "I-DURATION": 31,
+    "I-FAMILY_HISTORY": 33,
+    "I-FREQUENCY": 36,
+    "I-HEIGHT": 37,
+    "I-HISTORY": 40,
+    "I-LAB_VALUE": 41,
+    "I-MASS": 43,
+    "I-MEDICATION": 45,
+    "I-NONBIOLOGICAL_LOCATION": 47,
+    "I-OCCUPATION": 49,
+    "I-OTHER_ENTITY": 52,
+    "I-OTHER_EVENT": 54,
+    "I-OUTCOME": 55,
+    "I-PERSONAL_BACKGROUND": 57,
+    "I-QUALITATIVE_CONCEPT": 60,
+    "I-QUANTITATIVE_CONCEPT": 61,
+    "I-SEVERITY": 64,
+    "I-SEX": 66,
+    "I-SHAPE": 68,
+    "I-SIGN_SYMPTOM": 70,
+    "I-SUBJECT": 72,
+    "I-TEXTURE": 74,
+    "I-THERAPEUTIC_PROCEDURE": 76,
+    "I-TIME": 77,
+    "I-VOLUME": 80,
+    "I-WEIGHT": 81,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0869169ee520de1aae48681b98e1042b3406f8dfd86a0a06009dfc2fb518eb3b
+size 735605900

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8280c5db6559eca6ebac8e65c3555c0d423372e0769d5326e1890367e110c0e6
+size 4463