javicorvi/pretoxtm-sentence-classifier

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+- f1
+model-index:
+- name: pretoxtm-sentence-classifier
+  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. -->
+
+# pretoxtm-sentence-classifier
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0802
+- Precision: 0.9778
+- Recall: 0.9801
+- Accuracy: 0.9795
+- F1: 0.9789
+
+## 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: 7.755382954990098e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
+| No log        | 1.0   | 257  | 0.1410          | 0.9593    | 0.9684 | 0.9636   | 0.9628 |
+| 0.1997        | 2.0   | 514  | 0.0802          | 0.9778    | 0.9801 | 0.9795   | 0.9789 |
+| 0.1997        | 3.0   | 771  | 0.1103          | 0.9824    | 0.9848 | 0.9841   | 0.9836 |
+| 0.0514        | 4.0   | 1028 | 0.1139          | 0.9798    | 0.9829 | 0.9818   | 0.9813 |
+| 0.0514        | 5.0   | 1285 | 0.1208          | 0.9804    | 0.9821 | 0.9818   | 0.9812 |
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-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": "NO_PRETOX_REL",
+    "1": "PRETOX_REL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NO_PRETOX_REL": 0,
+    "PRETOX_REL": 1
+  },
+  "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": "4.39.2",
+  "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:fe9c64c65528f684f2f6150137c58978bb21575884774b713d2cbd36f112df19
+size 437958648

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
+    },
+    "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02921f0a11a038bbebe5d34b968c7edcf6b3947e1b627936a700e9055974e7a4
+size 4920