NHS-BiomedNLP-BiomedBERT-hypop-512

README.md

@@ -1,68 +1,68 @@
----
-license: mit
-base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
-tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- precision
-- recall
-- f1
-model-index:
-- name: NHS-BiomedNLP-BiomedBERT-hypop-512
- 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-BiomedNLP-BiomedBERT-hypop-512
-
-This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5390
-- Accuracy: 0.8120
-- Precision: 0.8119
-- Recall: 0.8028
-- F1: 0.8059
-
-## 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 |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.124 | 1.0 | 397 | 0.4029 | 0.8177 | 0.8146 | 0.8129 | 0.8137 |
-| 0.0594 | 2.0 | 794 | 0.4561 | 0.8246 | 0.8245 | 0.8161 | 0.8192 |
-| 0.1105 | 3.0 | 1191 | 0.5390 | 0.8120 | 0.8119 | 0.8028 | 0.8059 |
-
-
-### Framework versions
-
-- Transformers 4.38.2
-- Pytorch 2.2.2+cpu
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+---
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: NHS-BiomedNLP-BiomedBERT-hypop-512
+ 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-BiomedNLP-BiomedBERT-hypop-512
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3839
+- Accuracy: 0.8269
+- Precision: 0.8228
+- Recall: 0.8237
+- F1: 0.8232
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.124 | 1.0 | 397 | 0.4029 | 0.8177 | 0.8146 | 0.8129 | 0.8137 |
+| 0.0594 | 2.0 | 794 | 0.4561 | 0.8246 | 0.8245 | 0.8161 | 0.8192 |
+| 0.1105 | 3.0 | 1191 | 0.5390 | 0.8120 | 0.8119 | 0.8028 | 0.8059 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.2+cpu
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -1,34 +1,34 @@
-{
- "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
- "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
-}
+{
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
+ "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
+}

runs/Apr28_15-03-26_NCATS-2265430-P/events.out.tfevents.1714484123.NCATS-2265430-P.5044.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc586a12c95ca5d8213c6de60c3e23695bbecfa1bbf23ba9df0030edf47d36e
+size 560

special_tokens_map.json

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

tokenizer_config.json

@@ -1,57 +1,57 @@
-{
- "added_tokens_decoder": {
- "0": {
- "content": "[PAD]",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "1": {
- "content": "[UNK]",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "2": {
- "content": "[CLS]",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "3": {
- "content": "[SEP]",
- "lstrip": false,
- "normalized": false,
- "rstrip": false,
- "single_word": false,
- "special": true
- },
- "4": {
- "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]"
-}
+{
+ "added_tokens_decoder": {
+ "0": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "[UNK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "[CLS]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "[SEP]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "4": {
+ "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]"
+}