Finetuned BioLinkBERT model with capition and reference of synthetic dataset

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "michiyasunaga/BioLinkBERT-base",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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": "medical",
+    "1": "non-medical"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "false": 0,
+    "true": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28895
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecaca76e3e2cc132ffa8fc7ca150eaa67ed37e50759515a759fa2c16de879532
+size 432960488

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b9b05513439a318812d9fb4ea70645ea21851336ec7d0e92f16a5cde18b90e
+size 866042106

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40bd9141009165e923963552b2409da2ca8cad007fc9f571eff5b9475ae26b8
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc8cfc3c0c7c3e9ca7a2f291ecebb32099d3d2a715930cba68b5e931884385b
+size 1064

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": 0.18560722470283508,
+  "best_model_checkpoint": "biolinkbert_caption_reference_RTX6000/checkpoint-1230",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 4.879099369049072,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2196,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 1.5588421821594238,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1697,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.92894387076986,
+      "eval_f1": 0.9240870898542597,
+      "eval_f1_medical": 0.9432884536923705,
+      "eval_f1_non_medical": 0.9048857260161489,
+      "eval_loss": 0.18560722470283508,
+      "eval_precision": 0.9266766962431328,
+      "eval_recall": 0.9217536238643151,
+      "eval_runtime": 100.9349,
+      "eval_samples_per_second": 96.904,
+      "eval_steps_per_second": 3.032,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 1.4866325855255127,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.135,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 2.8782901763916016,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1139,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9333401492689909,
+      "eval_f1": 0.9292895437603008,
+      "eval_f1_medical": 0.9462134961227521,
+      "eval_f1_non_medical": 0.9123655913978495,
+      "eval_loss": 0.2073008269071579,
+      "eval_precision": 0.928674499317921,
+      "eval_recall": 0.929922559124454,
+      "eval_runtime": 93.6114,
+      "eval_samples_per_second": 104.485,
+      "eval_steps_per_second": 3.269,
+      "step": 2460
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.071174050023808e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843895257e525b8c2be1a323b20f1714c4ff9a341bebebe19b083c4c5b53f45e
+size 5176