Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
+tags:
+- generated_from_keras_callback
+model-index:
+- name: judithrosell/PubMedBERT-ft-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. -->
+
+# judithrosell/PubMedBERT-ft-ner
+
+This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.3653
+- Validation Loss: 0.2258
+- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 23335, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.3653     | 0.2258          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 2,
+  "[MASK]": 4,
+  "[PAD]": 0,
+  "[SEP]": 3,
+  "[UNK]": 1
+}

config.json

@@ -0,0 +1,146 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-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-Organism_subdivision",
+    "1": "I-Pathological_formation",
+    "2": "I-Anatomical_system",
+    "3": "B-Immaterial_anatomical_entity",
+    "4": "I-GGP",
+    "5": "I-Organism",
+    "6": "I-CL",
+    "7": "B-Organism",
+    "8": "B-DNA",
+    "9": "I-Gene_or_gene_product",
+    "10": "I-Tissue",
+    "11": "B-Developing_anatomical_structure",
+    "12": "I-RNA",
+    "13": "I-CHEBI",
+    "14": "B-Multi-tissue_structure",
+    "15": "I-DNA",
+    "16": "B-GO",
+    "17": "O",
+    "18": "B-Cell",
+    "19": "I-Multi-tissue_structure",
+    "20": "B-cell_type",
+    "21": "I-Immaterial_anatomical_entity",
+    "22": "B-RNA",
+    "23": "B-Cancer",
+    "24": "I-Organism_subdivision",
+    "25": "B-protein",
+    "26": "B-Chemical",
+    "27": "I-protein",
+    "28": "I-Simple_chemical",
+    "29": "I-Disease",
+    "30": "I-Cellular_component",
+    "31": "I-Chemical",
+    "32": "B-Amino_acid",
+    "33": "I-Organism_substance",
+    "34": "I-Developing_anatomical_structure",
+    "35": "I-SO",
+    "36": "I-cell_type",
+    "37": "B-Tissue",
+    "38": "B-Organism_substance",
+    "39": "B-GGP",
+    "40": "B-cell_line",
+    "41": "B-CHEBI",
+    "42": "B-Organ",
+    "43": "B-Gene_or_gene_product",
+    "44": "I-Amino_acid",
+    "45": "B-Taxon",
+    "46": "I-GO",
+    "47": "I-Organ",
+    "48": "I-cell_line",
+    "49": "I-Cancer",
+    "50": "I-Cell",
+    "51": "B-SO",
+    "52": "B-Anatomical_system",
+    "53": "B-CL",
+    "54": "B-Simple_chemical",
+    "55": "B-Disease",
+    "56": "I-Taxon",
+    "57": "B-Cellular_component",
+    "58": "B-Pathological_formation"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Amino_acid": 32,
+    "B-Anatomical_system": 52,
+    "B-CHEBI": 41,
+    "B-CL": 53,
+    "B-Cancer": 23,
+    "B-Cell": 18,
+    "B-Cellular_component": 57,
+    "B-Chemical": 26,
+    "B-DNA": 8,
+    "B-Developing_anatomical_structure": 11,
+    "B-Disease": 55,
+    "B-GGP": 39,
+    "B-GO": 16,
+    "B-Gene_or_gene_product": 43,
+    "B-Immaterial_anatomical_entity": 3,
+    "B-Multi-tissue_structure": 14,
+    "B-Organ": 42,
+    "B-Organism": 7,
+    "B-Organism_subdivision": 0,
+    "B-Organism_substance": 38,
+    "B-Pathological_formation": 58,
+    "B-RNA": 22,
+    "B-SO": 51,
+    "B-Simple_chemical": 54,
+    "B-Taxon": 45,
+    "B-Tissue": 37,
+    "B-cell_line": 40,
+    "B-cell_type": 20,
+    "B-protein": 25,
+    "I-Amino_acid": 44,
+    "I-Anatomical_system": 2,
+    "I-CHEBI": 13,
+    "I-CL": 6,
+    "I-Cancer": 49,
+    "I-Cell": 50,
+    "I-Cellular_component": 30,
+    "I-Chemical": 31,
+    "I-DNA": 15,
+    "I-Developing_anatomical_structure": 34,
+    "I-Disease": 29,
+    "I-GGP": 4,
+    "I-GO": 46,
+    "I-Gene_or_gene_product": 9,
+    "I-Immaterial_anatomical_entity": 21,
+    "I-Multi-tissue_structure": 19,
+    "I-Organ": 47,
+    "I-Organism": 5,
+    "I-Organism_subdivision": 24,
+    "I-Organism_substance": 33,
+    "I-Pathological_formation": 1,
+    "I-RNA": 12,
+    "I-SO": 35,
+    "I-Simple_chemical": 28,
+    "I-Taxon": 56,
+    "I-Tissue": 10,
+    "I-cell_line": 48,
+    "I-cell_type": 36,
+    "I-protein": 27,
+    "O": 17
+  },
+  "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": "4.34.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

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:dfaa831fc5c0a8cad95803bf58a4cba62b3ae9c0df55291bb589a7b16f7a095f
+size 436021428

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
+    }
+  },
+  "additional_special_tokens": [],
+  "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]"
+}