End of training

README.md

@@ -0,0 +1,74 @@
+---
+base_model: dmis-lab/biobert-base-cased-v1.2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: biobert-base-cased-v1.2-finetuned-NER
+ 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-base-cased-v1.2-finetuned-NER
+
+This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0905
+- Accuracy: 0.9765
+- Precision (macro): 0.8596
+- Recall (macro): 0.8601
+- F1 (macro): 0.8563
+- Precision (micro): 0.9765
+- Recall (micro): 0.9765
+- F1 (micro): 0.9765
+
+## 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: 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 | Accuracy | Precision (macro) | Recall (macro) | F1 (macro) | Precision (micro) | Recall (micro) | F1 (micro) |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:----------:|:-----------------:|:--------------:|:----------:|
+| No log | 1.0 | 152 | 0.1382 | 0.9621 | 0.8016 | 0.6594 | 0.6754 | 0.9621 | 0.9621 | 0.9621 |
+| No log | 2.0 | 304 | 0.0907 | 0.9740 | 0.8363 | 0.7827 | 0.7993 | 0.9740 | 0.9740 | 0.9740 |
+| No log | 3.0 | 456 | 0.0811 | 0.9750 | 0.8661 | 0.8285 | 0.8261 | 0.9750 | 0.9750 | 0.9750 |
+| 0.1768 | 4.0 | 608 | 0.0829 | 0.9738 | 0.8322 | 0.8581 | 0.8410 | 0.9738 | 0.9738 | 0.9738 |
+| 0.1768 | 5.0 | 760 | 0.0786 | 0.9755 | 0.8350 | 0.8737 | 0.8526 | 0.9755 | 0.9755 | 0.9755 |
+| 0.1768 | 6.0 | 912 | 0.0866 | 0.9766 | 0.8539 | 0.8491 | 0.8490 | 0.9766 | 0.9766 | 0.9766 |
+| 0.0496 | 7.0 | 1064 | 0.0828 | 0.9757 | 0.8454 | 0.8563 | 0.8494 | 0.9757 | 0.9757 | 0.9757 |
+| 0.0496 | 8.0 | 1216 | 0.0932 | 0.9754 | 0.8416 | 0.8622 | 0.8511 | 0.9754 | 0.9754 | 0.9754 |
+| 0.0496 | 9.0 | 1368 | 0.0939 | 0.9752 | 0.8368 | 0.8617 | 0.8483 | 0.9752 | 0.9752 | 0.9752 |
+| 0.0297 | 10.0 | 1520 | 0.0955 | 0.9759 | 0.8426 | 0.8597 | 0.8500 | 0.9759 | 0.9759 | 0.9759 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,49 @@
+{
+ "_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
+ "architectures": [
+ "BertForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4",
+ "5": "LABEL_5",
+ "6": "LABEL_6",
+ "7": "LABEL_7",
+ "8": "LABEL_8",
+ "9": "LABEL_9"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4,
+ "LABEL_5": 5,
+ "LABEL_6": 6,
+ "LABEL_7": 7,
+ "LABEL_8": 8,
+ "LABEL_9": 9
+ },
+ "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": "4.41.2",
+ "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 sha256:0dc552ab5a65d4e7d2bc1e2b0773c83dac27ba4d8eff3670d6e734439382d333
+size 430932816

runs/Jul09_06-59-19_7cdfbbe1be93/events.out.tfevents.1720508361.7cdfbbe1be93.345.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e0a277e49b7aa1c35d98121162fcca9132ae6b52608b9ba5c58689a41333fbc
+size 6288

runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720508739.7cdfbbe1be93.345.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbda90872038303c389bbee65cc04c0cfb324f2e3ba1d95bf59c3fd3e7de569
+size 12943

runs/Jul09_07-05-38_7cdfbbe1be93/events.out.tfevents.1720511185.7cdfbbe1be93.345.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e0846faa5d334be8fff45aa54fd2cf41f37eea35b8cc1084746f513a7a6569
+size 757

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": 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 sha256:842ebcfcd4df2b73ec2c46d3863bb03ccf2890aa2c5e769126a262e55610f714
+size 5112