Bioformer-16L finetuned on caption and reference text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bioformers/bioformer-16L",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "medical",
+    "1": "non-medical"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "false": 0,
+    "true": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "bert",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 16,
+  "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": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37e75863a62febf191f009d6e1bdb2214bed8c4bae990365471c3b218a6cfe4f
+size 166101712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b02dea93411aa8e1a2996c34fd49ff5f145d8105e9604607935754d766faa11
+size 332363130

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ce42163fbe4e2683e380aa3b8649d8e053e2fce2868fb3c87b16109b1831bf
+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
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": false,
+  "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": 0.17314428091049194,
+  "best_model_checkpoint": "bioformer16L_caption_reference_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": 6.706948757171631,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2407,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 1.3687267303466797,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1735,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9312953685717207,
+      "eval_f1": 0.927173283220003,
+      "eval_f1_medical": 0.9444995044598612,
+      "eval_f1_non_medical": 0.9098470619801449,
+      "eval_loss": 0.17314428091049194,
+      "eval_precision": 0.9262681850675076,
+      "eval_recall": 0.928118633114136,
+      "eval_runtime": 45.6262,
+      "eval_samples_per_second": 214.372,
+      "eval_steps_per_second": 6.707,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 3.611739158630371,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.1481,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 4.197986602783203,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1262,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9335446273387179,
+      "eval_f1": 0.928879727140856,
+      "eval_f1_medical": 0.9470942536220088,
+      "eval_f1_non_medical": 0.9106652006597031,
+      "eval_loss": 0.19185571372509003,
+      "eval_precision": 0.9323681847557893,
+      "eval_recall": 0.9258256103438091,
+      "eval_runtime": 45.171,
+      "eval_samples_per_second": 216.533,
+      "eval_steps_per_second": 6.774,
+      "step": 2460
+    },
+    {
+      "epoch": 2.032520325203252,
+      "grad_norm": 4.785476207733154,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.1146,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 8.604289054870605,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0779,
+      "step": 3000
+    },
+    {
+      "epoch": 2.845528455284553,
+      "grad_norm": 7.571163654327393,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 0.0902,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9337491054084449,
+      "eval_f1": 0.9294934079365336,
+      "eval_f1_medical": 0.9468154957321077,
+      "eval_f1_non_medical": 0.9121713201409596,
+      "eval_loss": 0.23544831573963165,
+      "eval_precision": 0.9302875262434688,
+      "eval_recall": 0.9287260343031765,
+      "eval_runtime": 45.0337,
+      "eval_samples_per_second": 217.193,
+      "eval_steps_per_second": 6.795,
+      "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": 1.0352847592113792e+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:de86408b569dd9e1bfcbfb5c91074eec691a42f530d3a9e5402e582c6f641fe7
+size 5176