Upload 10 files

README (8).md

@@ -0,0 +1,67 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: Bio_ClinicalBERT-finetuned-medicalcondition
+  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. -->
+
+# Bio_ClinicalBERT-finetuned-medicalcondition
+
+This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7201
+- F1 Score: 0.8254
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1 Score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.8002        | 1.0   | 1772  | 0.6327          | 0.7759   |
+| 0.5933        | 2.0   | 3544  | 0.5906          | 0.7934   |
+| 0.5015        | 3.0   | 5316  | 0.5768          | 0.8033   |
+| 0.4265        | 4.0   | 7088  | 0.5792          | 0.8099   |
+| 0.3698        | 5.0   | 8860  | 0.6030          | 0.8109   |
+| 0.3229        | 6.0   | 10632 | 0.6366          | 0.8167   |
+| 0.2907        | 7.0   | 12404 | 0.6671          | 0.8198   |
+| 0.2649        | 8.0   | 14176 | 0.6850          | 0.8237   |
+| 0.2477        | 9.0   | 15948 | 0.7072          | 0.8247   |
+| 0.2348        | 10.0  | 17720 | 0.7201          | 0.8254   |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.8.0
+- Tokenizers 0.13.2

config (3).json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Pain",
+    "1": "Depression",
+    "2": "High Blood Pressure",
+    "3": "Anxiety",
+    "4": "Migraine",
+    "5": "Diabetes, Type 2",
+    "6": "Weight Loss",
+    "7": "Insomnia",
+    "8": "Obesity"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anxiety": 3,
+    "Depression": 1,
+    "Diabetes, Type 2": 5,
+    "High Blood Pressure": 2,
+    "Insomnia": 7,
+    "Migraine": 4,
+    "Obesity": 8,
+    "Pain": 0,
+    "Weight Loss": 6
+  },
+  "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": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

gitattributes (8)

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

gitignore (1)

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

pytorch_model (3).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479fc13fd4c709ea943882bbd5c2d6216626c2ae31714a60f438f58b98d71b45
+size 433341557

special_tokens_map (2).json

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

tokenizer_config (2).json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args (1).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd78d48635bfa07210646f92a2c933c8b6bd47382e7e5d36585814d2fad8f5d9
+size 3451