medbioinformatics/biobert-v1.1-text-classifier

README.md

@@ -0,0 +1,69 @@
+---
+base_model: dmis-lab/biobert-v1.1
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+- f1
+model-index:
+- name: biobert-v1.1-text-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. -->
+
+# biobert-v1.1-text-classifier
+
+This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3062
+- Precision: 0.9119
+- Recall: 0.9097
+- Accuracy: 0.9097
+- F1: 0.9098
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
+| No log        | 1.0   | 154  | 0.3601          | 0.8662    | 0.8636 | 0.8633   | 0.8642 |
+| No log        | 2.0   | 308  | 0.3202          | 0.8942    | 0.8815 | 0.8820   | 0.8827 |
+| No log        | 3.0   | 462  | 0.2774          | 0.9107    | 0.9072 | 0.9072   | 0.9074 |
+| 0.3692        | 4.0   | 616  | 0.3064          | 0.9052    | 0.9015 | 0.9015   | 0.9017 |
+| 0.3692        | 5.0   | 770  | 0.3062          | 0.9119    | 0.9097 | 0.9097   | 0.9098 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dmis-lab/biobert-v1.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "marker/mechanism",
+    "1": "therapeutic",
+    "2": "unrelated"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "marker/mechanism": 0,
+    "therapeutic": 1,
+    "unrelated": 2
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fca787cdcff81b1cbbd33e6c00276857d24aeaba0eb4ef9a833dd8a633eeab
+size 433273844

runs/Feb16_08-50-39_1840cdbf14a3/events.out.tfevents.1708073440.1840cdbf14a3.743.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e94a6df8b6c472cec5cabf36e983f86eb68d41be48c2acaf83eab1f26cc80851
+size 4998

runs/Feb16_08-57-01_1840cdbf14a3/events.out.tfevents.1708073822.1840cdbf14a3.743.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e7bddd3500c9222d3190d34369b521c9a11e914b7bc4ca53f4c54ebf3b6472
+size 7397

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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "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:eb96ff4aab5770db04b2f8d0e4cd3b703f88c0d41a8e3d0dabdba4caeb3bb7c3
+size 4664