Model save

README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: BiomedNLP_BiomedBERT_base
+  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. -->
+
+# BiomedNLP_BiomedBERT_base
+
+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: 0.4483
+- Precision: 0.6219
+- Recall: 0.5782
+- F1: 0.5993
+- Accuracy: 0.9302
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 3407
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.2128        | 1.0   | 115  | 0.4881          | 0.1072    | 0.0495 | 0.0677 | 0.8566   |
+| 0.2669        | 2.0   | 230  | 0.3105          | 0.4019    | 0.4505 | 0.4248 | 0.9064   |
+| 0.1124        | 3.0   | 345  | 0.2825          | 0.5572    | 0.5136 | 0.5345 | 0.9216   |
+| 0.0636        | 4.0   | 460  | 0.3006          | 0.5889    | 0.5370 | 0.5618 | 0.9237   |
+| 0.0479        | 5.0   | 575  | 0.3030          | 0.6450    | 0.5406 | 0.5882 | 0.9304   |
+| 0.0309        | 6.0   | 690  | 0.3314          | 0.6357    | 0.5533 | 0.5917 | 0.9293   |
+| 0.0211        | 7.0   | 805  | 0.3425          | 0.6203    | 0.5584 | 0.5877 | 0.9299   |
+| 0.0185        | 8.0   | 920  | 0.3703          | 0.5995    | 0.5883 | 0.5939 | 0.9259   |
+| 0.0136        | 9.0   | 1035 | 0.3786          | 0.6474    | 0.5747 | 0.6089 | 0.9307   |
+| 0.0109        | 10.0  | 1150 | 0.3644          | 0.6310    | 0.5880 | 0.6088 | 0.9306   |
+| 0.0088        | 11.0  | 1265 | 0.3896          | 0.6264    | 0.5868 | 0.6060 | 0.9302   |
+| 0.0074        | 12.0  | 1380 | 0.4023          | 0.6209    | 0.5860 | 0.6029 | 0.9306   |
+| 0.0061        | 13.0  | 1495 | 0.4580          | 0.6274    | 0.5299 | 0.5746 | 0.9265   |
+| 0.0054        | 14.0  | 1610 | 0.4324          | 0.6126    | 0.5685 | 0.5897 | 0.9285   |
+| 0.0046        | 15.0  | 1725 | 0.4126          | 0.6175    | 0.5951 | 0.6061 | 0.9309   |
+| 0.0039        | 16.0  | 1840 | 0.4305          | 0.6130    | 0.5934 | 0.6030 | 0.9288   |
+| 0.0038        | 17.0  | 1955 | 0.4329          | 0.6155    | 0.5806 | 0.5975 | 0.9295   |
+| 0.003         | 18.0  | 2070 | 0.4374          | 0.6180    | 0.5854 | 0.6012 | 0.9301   |
+| 0.0031        | 19.0  | 2185 | 0.4525          | 0.625     | 0.5750 | 0.5990 | 0.9304   |
+| 0.0028        | 20.0  | 2300 | 0.4483          | 0.6219    | 0.5782 | 0.5993 | 0.9302   |
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.2
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CellLine",
+    "1": "I-Tissue",
+    "2": "B-Tissue",
+    "3": "I-CellType",
+    "4": "B-CellType",
+    "5": "I-CellLine",
+    "6": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CellLine": 0,
+    "B-CellType": 4,
+    "B-Tissue": 2,
+    "I-CellLine": 5,
+    "I-CellType": 3,
+    "I-Tissue": 1,
+    "O": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
+  "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:d3cdde3077e41f05681793c6200c858995ff90ecec6350d6352dc37f42c932d1
+size 435611468

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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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 sha256:58de44b767f87a9d735be0bdb274e63ffb309a02b75583fe7b93e9368959757a
+size 5560