pubmedbert finetuned model on 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:eb34b1e38284536062f0fd88282fd8a00f4808070e4b1ad0f25d2317e1e7a9d5
+size 437958648

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24219c04611344a883c18bf1edf8166da0ba01769ddf72b4ebc00b02b154daa4
+size 876038394

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c9d6b7ddb46e6f6ce8a314b070515c1303e9c8eb3a9acef0ea2ac4ca5bd792
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b957cec6154bcedd6e0296ef5735a7871ef230fe46097ee439ea17aba9b686ba
+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 +1,152 @@
+{
+  "best_metric": 0.1734582930803299,
+  "best_model_checkpoint": "pubmedbert_caption_RTX6000/checkpoint-1230",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 4.645663738250732,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2075,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 5.587854385375977,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1702,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9332379102341274,
+      "eval_f1": 0.928674632625657,
+      "eval_f1_medical": 0.9467156262749898,
+      "eval_f1_non_medical": 0.9106336389763241,
+      "eval_loss": 0.1734582930803299,
+      "eval_precision": 0.9312915820758167,
+      "eval_recall": 0.9263152623151424,
+      "eval_runtime": 68.2248,
+      "eval_samples_per_second": 143.364,
+      "eval_steps_per_second": 4.485,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 2.3974437713623047,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.1389,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 2.506718397140503,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1184,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9309886514671302,
+      "eval_f1": 0.9269715540062402,
+      "eval_f1_medical": 0.9440993788819876,
+      "eval_f1_non_medical": 0.9098437291304928,
+      "eval_loss": 0.2099289894104004,
+      "eval_precision": 0.9254099444591377,
+      "eval_recall": 0.9286608969105821,
+      "eval_runtime": 67.9715,
+      "eval_samples_per_second": 143.899,
+      "eval_steps_per_second": 4.502,
+      "step": 2460
+    },
+    {
+      "epoch": 2.032520325203252,
+      "grad_norm": 6.744129180908203,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.1077,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 6.095327377319336,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0688,
+      "step": 3000
+    },
+    {
+      "epoch": 2.845528455284553,
+      "grad_norm": 3.4065370559692383,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 0.0746,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9324199979552193,
+      "eval_f1": 0.9280287669371694,
+      "eval_f1_medical": 0.9458063458227433,
+      "eval_f1_non_medical": 0.9102511880515954,
+      "eval_loss": 0.27543091773986816,
+      "eval_precision": 0.9291365269492087,
+      "eval_recall": 0.9269721217289725,
+      "eval_runtime": 68.447,
+      "eval_samples_per_second": 142.899,
+      "eval_steps_per_second": 4.471,
+      "step": 3690
+    },
+    {
+      "epoch": 3.252032520325203,
+      "grad_norm": 0.23066511750221252,
+      "learning_rate": 1.048780487804878e-05,
+      "loss": 0.0512,
+      "step": 4000
+    },
+    {
+      "epoch": 3.658536585365854,
+      "grad_norm": 3.5666403770446777,
+      "learning_rate": 8.048780487804879e-06,
+      "loss": 0.0439,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9324199979552193,
+      "eval_f1": 0.9285368368262559,
+      "eval_f1_medical": 0.9451952574413398,
+      "eval_f1_non_medical": 0.9118784162111718,
+      "eval_loss": 0.35453397035598755,
+      "eval_precision": 0.9267038108683107,
+      "eval_recall": 0.930549725836648,
+      "eval_runtime": 67.9947,
+      "eval_samples_per_second": 143.849,
+      "eval_steps_per_second": 4.5,
+      "step": 4920
+    }
+  ],
+  "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": 3.436358649641088e+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 sha256:58aefb422511a44b3f045188ce5a98fdd8106c308b3c35857de25134048a06fa
+size 5176