akmaldika/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-medical-question-classifier

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0078
+- F1: 0.9961
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0215        | 1.0   | 897  | 0.0172          | 0.9848 |
+| 0.0014        | 2.0   | 1794 | 0.0149          | 0.9870 |
+| 0.0006        | 3.0   | 2691 | 0.0078          | 0.9961 |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "causes",
+    "1": "complications",
+    "2": "considerations",
+    "3": "desc",
+    "4": "dont answer",
+    "5": "exams and tests",
+    "6": "frequency",
+    "7": "general",
+    "8": "genetic changes",
+    "9": "information",
+    "10": "inheritance",
+    "11": "outlook",
+    "12": "precaution",
+    "13": "prevention",
+    "14": "research",
+    "15": "stages",
+    "16": "support groups",
+    "17": "susceptibility",
+    "18": "symptoms",
+    "19": "treatment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "causes": 0,
+    "complications": 1,
+    "considerations": 2,
+    "desc": 3,
+    "dont answer": 4,
+    "exams and tests": 5,
+    "frequency": 6,
+    "general": 7,
+    "genetic changes": 8,
+    "information": 9,
+    "inheritance": 10,
+    "outlook": 11,
+    "precaution": 12,
+    "prevention": 13,
+    "research": 14,
+    "stages": 15,
+    "support groups": 16,
+    "susceptibility": 17,
+    "symptoms": 18,
+    "treatment": 19
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159793ceeb76e559c05b6a484acd28845a6d62508e4753e875911c822c7d7509
+size 438014016

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb13d1ecb68e1c4e02e1458bf7b5342efd919f74be3c1aed1eb841ef70d0de2
+size 5240