Finetuned Bioformer-16L model with capition only of synthetic dataset

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:fa7161ec8cbda0691c83be3f153eeb80db89d8d12c62822fd85546468f808206
+size 166101712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d2a597e3ca991fd9f8550f68f3cbffb9c5cf056a7f94ea5fa57cce55747c93
+size 332363130

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405c4938f32e18909820b7cf7ac7e4123b68633c43f0cb6cdd62b960132809ea
+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
+    },
+    "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 +1,152 @@
+{
+  "best_metric": 0.19506023824214935,
+  "best_model_checkpoint": "bioformer16L_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": 4.495114803314209,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.256,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 2.5886974334716797,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1859,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9271035681423168,
+      "eval_f1": 0.9220692013036642,
+      "eval_f1_medical": 0.9418765794407761,
+      "eval_f1_non_medical": 0.9022618231665525,
+      "eval_loss": 0.19506023824214935,
+      "eval_precision": 0.9249732755411849,
+      "eval_recall": 0.9194829650061407,
+      "eval_runtime": 34.6825,
+      "eval_samples_per_second": 282.015,
+      "eval_steps_per_second": 8.823,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 2.54653263092041,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.1571,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 2.3185017108917236,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1303,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.92516102647991,
+      "eval_f1": 0.921045875731096,
+      "eval_f1_medical": 0.9390710837356417,
+      "eval_f1_non_medical": 0.9030206677265501,
+      "eval_loss": 0.2094709575176239,
+      "eval_precision": 0.9184306018002388,
+      "eval_recall": 0.9240747625361165,
+      "eval_runtime": 34.5371,
+      "eval_samples_per_second": 283.202,
+      "eval_steps_per_second": 8.86,
+      "step": 2460
+    },
+    {
+      "epoch": 2.032520325203252,
+      "grad_norm": 4.058623313903809,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.1238,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 5.887447834014893,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0884,
+      "step": 3000
+    },
+    {
+      "epoch": 2.845528455284553,
+      "grad_norm": 3.797337055206299,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 0.092,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9272058071771803,
+      "eval_f1": 0.9219373155502308,
+      "eval_f1_medical": 0.9422171725369258,
+      "eval_f1_non_medical": 0.901657458563536,
+      "eval_loss": 0.27733102440834045,
+      "eval_precision": 0.9264226794905697,
+      "eval_recall": 0.9181447502548421,
+      "eval_runtime": 34.4489,
+      "eval_samples_per_second": 283.927,
+      "eval_steps_per_second": 8.883,
+      "step": 3690
+    },
+    {
+      "epoch": 3.252032520325203,
+      "grad_norm": 11.003833770751953,
+      "learning_rate": 1.048780487804878e-05,
+      "loss": 0.0625,
+      "step": 4000
+    },
+    {
+      "epoch": 3.658536585365854,
+      "grad_norm": 11.000012397766113,
+      "learning_rate": 8.048780487804879e-06,
+      "loss": 0.059,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9267968510377262,
+      "eval_f1": 0.9224128655389552,
+      "eval_f1_medical": 0.9408557739963654,
+      "eval_f1_non_medical": 0.903969957081545,
+      "eval_loss": 0.30652934312820435,
+      "eval_precision": 0.9214772563975018,
+      "eval_recall": 0.9233923856098107,
+      "eval_runtime": 34.3959,
+      "eval_samples_per_second": 284.366,
+      "eval_steps_per_second": 8.896,
+      "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": 1.1766206373267072e+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:ef97de208b335bbbc57a5ea95c0d27d5147f6881ee82972db854d731ee78bf06
+size 5176