Bioformer8L finetuned on caption and reference

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bioformers/bioformer-8L",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "medical",
+    "1": "non-medical"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "false": 0,
+    "true": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "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:c4b5a277fedfb6854ce96cdb3f5033eedef964dd303c275badc180a6e8ab6c03
+size 170112544

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906549280b545654a7880219f1be8769e357e4f86c523edfd7b8840a3448ad11
+size 340308090

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c601a01fb930768137c76e791e66a1c1a368c64ffb6496d523c371d6d7430fd0
+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 +1,7 @@
+{
+  "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 +1,89 @@
+{
+  "best_metric": 0.17856432497501373,
+  "best_model_checkpoint": "bioformer8L_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": 8.241156578063965,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2277,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 2.205291986465454,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.177,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9276147633166343,
+      "eval_f1": 0.9222332155896071,
+      "eval_f1_medical": 0.9426906265177271,
+      "eval_f1_non_medical": 0.9017758046614872,
+      "eval_loss": 0.17856432497501373,
+      "eval_precision": 0.9277090451077986,
+      "eval_recall": 0.9177374028102576,
+      "eval_runtime": 37.413,
+      "eval_samples_per_second": 261.433,
+      "eval_steps_per_second": 8.179,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 3.5154032707214355,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.1466,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 3.8458199501037598,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1232,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.929352826909314,
+      "eval_f1": 0.9248187483559904,
+      "eval_f1_medical": 0.9432816219322006,
+      "eval_f1_non_medical": 0.9063558747797804,
+      "eval_loss": 0.20747286081314087,
+      "eval_precision": 0.9255804539078865,
+      "eval_recall": 0.9240820913256004,
+      "eval_runtime": 37.4622,
+      "eval_samples_per_second": 261.09,
+      "eval_steps_per_second": 8.168,
+      "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": 6162603809728128.0,
+  "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 sha256:97e28cedf350b1f6770309d1c5846b6342035a98d45f18baebaae7acb21e75ae
+size 5176