pubmedbert finetuned model on caption and reference text of synthetic data

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74aabb79f55360a62330a824a656c4178ea447a315e32a639e5a9d1dccbca482
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe807683dbbf39734dd8fe26e73ef5ebee76709ed069f6144944836e15caf378
+size 876038394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1009f72610c707071843ceb8911047082d96a67a4473a911b7d47836581eaade
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89efffcd74eff4bdde090bc0170c8689c86ba3b38a24022a1aa64dac7dd99e42
+size 1064

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": 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 +1,124 @@
+{
+  "best_metric": 0.16344858705997467,
+  "best_model_checkpoint": "pubmedbert_caption+ref_RTX6000/checkpoint-1230",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 7.820664405822754,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2074,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 2.407073974609375,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1646,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9358961251405786,
+      "eval_f1": 0.9313383960406174,
+      "eval_f1_medical": 0.9490285342655068,
+      "eval_f1_non_medical": 0.9136482578157279,
+      "eval_loss": 0.16344858705997467,
+      "eval_precision": 0.9352860582386011,
+      "eval_recall": 0.9279290617594869,
+      "eval_runtime": 93.0813,
+      "eval_samples_per_second": 105.08,
+      "eval_steps_per_second": 3.287,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 2.0749707221984863,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.131,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 3.7739999294281006,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1145,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9353849299662611,
+      "eval_f1": 0.9315011393590601,
+      "eval_f1_medical": 0.9478117258464079,
+      "eval_f1_non_medical": 0.9151905528717122,
+      "eval_loss": 0.1923774778842926,
+      "eval_precision": 0.9306285500446541,
+      "eval_recall": 0.9324104388612393,
+      "eval_runtime": 92.7173,
+      "eval_samples_per_second": 105.493,
+      "eval_steps_per_second": 3.3,
+      "step": 2460
+    },
+    {
+      "epoch": 2.032520325203252,
+      "grad_norm": 9.552169799804688,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.1044,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 0.6083847284317017,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0656,
+      "step": 3000
+    },
+    {
+      "epoch": 2.845528455284553,
+      "grad_norm": 2.998614549636841,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 0.0744,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9359983641754421,
+      "eval_f1": 0.9318359818739486,
+      "eval_f1_medical": 0.9486801114936875,
+      "eval_f1_non_medical": 0.9149918522542096,
+      "eval_loss": 0.23488560318946838,
+      "eval_precision": 0.9329783496995749,
+      "eval_recall": 0.9307471811921053,
+      "eval_runtime": 92.6853,
+      "eval_samples_per_second": 105.529,
+      "eval_steps_per_second": 3.301,
+      "step": 3690
+    }
+  ],
+  "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": 3.106719963933312e+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 sha256:173e29ba039215cd3eebaaa0dd4c794b677eddc6ff67d63c16bc6f4bbf0a0975
+size 5176