NHS-bluebert-binary-random

README.md

@@ -0,0 +1,68 @@
+---
+license: cc0-1.0
+base_model: bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: NHS-bluebert-binary-random
+  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. -->
+
+# NHS-bluebert-binary-random
+
+This model is a fine-tuned version of [bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12](https://huggingface.co/bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5886
+- Accuracy: 0.8126
+- Precision: 0.8063
+- Recall: 0.8047
+- F1: 0.8055
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.0522        | 1.0   | 397  | 0.4105          | 0.8114   | 0.8044    | 0.8094 | 0.8064 |
+| 0.0734        | 2.0   | 794  | 0.4493          | 0.7918   | 0.7894    | 0.7994 | 0.7894 |
+| 1.3945        | 3.0   | 1191 | 0.5886          | 0.8126   | 0.8063    | 0.8047 | 0.8055 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "the paper is not a primary experimental study in rare disease or the study is not directly investigating the natural history of a disease",
+    "1": "its primary contribution centers on observing the time course of a rare disease"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "its primary contribution centers on observing the time course of a rare disease": 1,
+    "the paper is not a primary experimental study in rare disease or the study is not directly investigating the natural history of a disease": 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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "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 sha256:217986ea59186a6f7b4d0329bb7ac9fc0218e1d3aecc3cc6b04d27bfb82ee344
+size 437958648

runs/Mar26_06-50-52_d4944df8337e/events.out.tfevents.1711435858.d4944df8337e.190.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aecce702fb21e9eeaa5cd04a49d7133aac83cce878d2ad9e684a496f4184948
+size 257628

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5accd6e3b6f5a04f2c1c05f60aaaf0977decec9ca11d57f8a02e5197976c7ae9
+size 4920