Upload 8 files

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "Dr-BERT/DrBERT-4GB-CP-PubMedBERT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-ANAT",
+    "2": "I-ANAT",
+    "3": "B-CHEM",
+    "4": "I-CHEM",
+    "5": "B-DEVI",
+    "6": "I-DEVI",
+    "7": "B-DISO",
+    "8": "I-DISO",
+    "9": "B-GEOG",
+    "10": "I-GEOG",
+    "11": "B-LIVB",
+    "12": "I-LIVB",
+    "13": "B-OBJC",
+    "14": "I-OBJC",
+    "15": "B-PHEN",
+    "16": "I-PHEN",
+    "17": "B-PHYS",
+    "18": "I-PHYS",
+    "19": "B-PROC",
+    "20": "I-PROC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANAT": 1,
+    "B-CHEM": 3,
+    "B-DEVI": 5,
+    "B-DISO": 7,
+    "B-GEOG": 9,
+    "B-LIVB": 11,
+    "B-OBJC": 13,
+    "B-PHEN": 15,
+    "B-PHYS": 17,
+    "B-PROC": 19,
+    "I-ANAT": 2,
+    "I-CHEM": 4,
+    "I-DEVI": 6,
+    "I-DISO": 8,
+    "I-GEOG": 10,
+    "I-LIVB": 12,
+    "I-OBJC": 14,
+    "I-PHEN": 16,
+    "I-PHYS": 18,
+    "I-PROC": 20,
+    "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "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 sha256:826ba6a1d1520236b4ba8f493dc584915055a2e2a0c941364bf9d16f6f311983
+size 435654532

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ddf17adc19b1e6347170dc0f4657d659b6ac3bf2054fbb1f3f4ea32a1e0c00
+size 871428666

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
+    },
+    "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,
+  "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]"
+}

trainer_config.yml

@@ -0,0 +1,11 @@
+learning_rate: 5.0e-05
+nb_training_epochs: 10
+dataloader_nb_workers: 0
+batch_size: 16
+seed: null
+gradient_accumulation_steps: 1
+do_metrics_in_training: false
+metric_to_track_lr: loss
+checkpoint_period: 1
+checkpoint_metric: loss
+minimize_checkpoint_metric: true