Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_keras_callback
+model-index:
+- name: LinYuting/bert-base-ner
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# LinYuting/bert-base-ner
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3846
+- Validation Loss: 0.0465
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 849, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.3846     | 0.0465          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- TensorFlow 2.11.0
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-ACCESSION_NUM",
+    "2": "I-ACCESSION_NUM",
+    "3": "B-ALLELE_FREQ",
+    "4": "I-ALLELE_FREQ",
+    "5": "B-AMINO_ACID_CHANGE",
+    "6": "I-AMINO_ACID_CHANGE",
+    "7": "B-ASSAY",
+    "8": "I-ASSAY",
+    "9": "B-BIOMARKER",
+    "10": "I-BIOMARKER",
+    "11": "B-CDNA_CHANGE",
+    "12": "I-CDNA_CHANGE",
+    "13": "B-CF_DNA_OR_AMP",
+    "14": "I-CF_DNA_OR_AMP",
+    "15": "B-CHROM",
+    "16": "I-CHROM",
+    "17": "B-COPY_NUM",
+    "18": "I-COPY_NUM",
+    "19": "B-COSMIC_ID",
+    "20": "I-COSMIC_ID",
+    "21": "B-COVERAGE",
+    "22": "I-COVERAGE",
+    "23": "B-DATE",
+    "24": "I-DATE",
+    "25": "B-EFFECT",
+    "26": "I-EFFECT",
+    "27": "B-EXON",
+    "28": "I-EXON",
+    "29": "B-GENE",
+    "30": "I-GENE",
+    "31": "B-NEG_BIOMARKER",
+    "32": "I-NEG_BIOMARKER",
+    "33": "B-OTHER_SENSITIVE_DRUGS",
+    "34": "I-OTHER_SENSITIVE_DRUGS",
+    "35": "B-PATIENT_ID",
+    "36": "I-PATIENT_ID",
+    "37": "B-PATIENT_NAME",
+    "38": "I-PATIENT_NAME",
+    "39": "B-POS_BIOMARKER",
+    "40": "I-POS_BIOMARKER",
+    "41": "B-REPORT_NO",
+    "42": "I-REPORT_NO",
+    "43": "B-RESISTANT_DRUGS",
+    "44": "I-RESISTANT_DRUGS",
+    "45": "B-RESULTS",
+    "46": "I-RESULTS",
+    "47": "B-SENSITIVE_DRUGS",
+    "48": "I-SENSITIVE_DRUGS",
+    "49": "B-THERAPIES",
+    "50": "I-THERAPIES",
+    "51": "B-TUMOR_TYPE",
+    "52": "I-TUMOR_TYPE",
+    "53": "B-VARIATION",
+    "54": "I-VARIATION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ACCESSION_NUM": 1,
+    "B-ALLELE_FREQ": 3,
+    "B-AMINO_ACID_CHANGE": 5,
+    "B-ASSAY": 7,
+    "B-BIOMARKER": 9,
+    "B-CDNA_CHANGE": 11,
+    "B-CF_DNA_OR_AMP": 13,
+    "B-CHROM": 15,
+    "B-COPY_NUM": 17,
+    "B-COSMIC_ID": 19,
+    "B-COVERAGE": 21,
+    "B-DATE": 23,
+    "B-EFFECT": 25,
+    "B-EXON": 27,
+    "B-GENE": 29,
+    "B-NEG_BIOMARKER": 31,
+    "B-OTHER_SENSITIVE_DRUGS": 33,
+    "B-PATIENT_ID": 35,
+    "B-PATIENT_NAME": 37,
+    "B-POS_BIOMARKER": 39,
+    "B-REPORT_NO": 41,
+    "B-RESISTANT_DRUGS": 43,
+    "B-RESULTS": 45,
+    "B-SENSITIVE_DRUGS": 47,
+    "B-THERAPIES": 49,
+    "B-TUMOR_TYPE": 51,
+    "B-VARIATION": 53,
+    "I-ACCESSION_NUM": 2,
+    "I-ALLELE_FREQ": 4,
+    "I-AMINO_ACID_CHANGE": 6,
+    "I-ASSAY": 8,
+    "I-BIOMARKER": 10,
+    "I-CDNA_CHANGE": 12,
+    "I-CF_DNA_OR_AMP": 14,
+    "I-CHROM": 16,
+    "I-COPY_NUM": 18,
+    "I-COSMIC_ID": 20,
+    "I-COVERAGE": 22,
+    "I-DATE": 24,
+    "I-EFFECT": 26,
+    "I-EXON": 28,
+    "I-GENE": 30,
+    "I-NEG_BIOMARKER": 32,
+    "I-OTHER_SENSITIVE_DRUGS": 34,
+    "I-PATIENT_ID": 36,
+    "I-PATIENT_NAME": 38,
+    "I-POS_BIOMARKER": 40,
+    "I-REPORT_NO": 42,
+    "I-RESISTANT_DRUGS": 44,
+    "I-RESULTS": 46,
+    "I-SENSITIVE_DRUGS": 48,
+    "I-THERAPIES": 50,
+    "I-TUMOR_TYPE": 52,
+    "I-VARIATION": 54,
+    "O": 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",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2683b4e780326037c703233dea6a3f0a2fd1883a2b961787f140f95d82a313ca
+size 431321252

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}