Bioformer8L finetuned on capition

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:d9fd37b93a061d4d79089af81aa0ae36e199fb576c2e4b77df1c4a819d95a52b
+size 170112544

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc908b9a245a560a87023613bfb0dd71a7aa7fd331862bf4e3ae1b39809d7e0
+size 340308090

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38b337faf3a4c597f45e8f671a0913efc818ea5051bb4ae476d843ed5edcf70
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04780ebe127daef6c93951a787dc090de88da8be795051f65c218819256add5b
+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 +1,187 @@
+{
+  "best_metric": 0.1951880156993866,
+  "best_model_checkpoint": "bioformer8L_caption_RTX6000/checkpoint-1230",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 6150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 6.299335956573486,
+      "learning_rate": 2.75609756097561e-05,
+      "loss": 0.2386,
+      "step": 500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 1.643288016319275,
+      "learning_rate": 2.5121951219512197e-05,
+      "loss": 0.1845,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9235252019220939,
+      "eval_f1": 0.9179996646545943,
+      "eval_f1_medical": 0.9392857142857143,
+      "eval_f1_non_medical": 0.8967136150234741,
+      "eval_loss": 0.1951880156993866,
+      "eval_precision": 0.9223852158649997,
+      "eval_recall": 0.9142873862649601,
+      "eval_runtime": 27.8883,
+      "eval_samples_per_second": 350.72,
+      "eval_steps_per_second": 10.972,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 2.678163766860962,
+      "learning_rate": 2.2682926829268295e-05,
+      "loss": 0.1505,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 2.3176321983337402,
+      "learning_rate": 2.024390243902439e-05,
+      "loss": 0.1284,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9270013291074533,
+      "eval_f1": 0.9224194379620252,
+      "eval_f1_medical": 0.9412732357295608,
+      "eval_f1_non_medical": 0.9035656401944895,
+      "eval_loss": 0.2104455977678299,
+      "eval_precision": 0.9225986393203021,
+      "eval_recall": 0.9222416990354869,
+      "eval_runtime": 28.2544,
+      "eval_samples_per_second": 346.176,
+      "eval_steps_per_second": 10.83,
+      "step": 2460
+    },
+    {
+      "epoch": 2.032520325203252,
+      "grad_norm": 4.071255683898926,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 0.1227,
+      "step": 2500
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 14.561558723449707,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 0.0809,
+      "step": 3000
+    },
+    {
+      "epoch": 2.845528455284553,
+      "grad_norm": 5.630990982055664,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 0.0881,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9278192413863613,
+      "eval_f1": 0.9233290940374888,
+      "eval_f1_medical": 0.9418834376028976,
+      "eval_f1_non_medical": 0.9047747504720799,
+      "eval_loss": 0.25612133741378784,
+      "eval_precision": 0.9232846377701289,
+      "eval_recall": 0.9233736416754945,
+      "eval_runtime": 27.9805,
+      "eval_samples_per_second": 349.564,
+      "eval_steps_per_second": 10.936,
+      "step": 3690
+    },
+    {
+      "epoch": 3.252032520325203,
+      "grad_norm": 16.422693252563477,
+      "learning_rate": 1.048780487804878e-05,
+      "loss": 0.0643,
+      "step": 4000
+    },
+    {
+      "epoch": 3.658536585365854,
+      "grad_norm": 3.8088247776031494,
+      "learning_rate": 8.048780487804879e-06,
+      "loss": 0.0567,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9209692260505061,
+      "eval_f1": 0.9165782775866363,
+      "eval_f1_medical": 0.9357172557172557,
+      "eval_f1_non_medical": 0.897439299456017,
+      "eval_loss": 0.3461480140686035,
+      "eval_precision": 0.9141722217469603,
+      "eval_recall": 0.9193323694864739,
+      "eval_runtime": 27.8584,
+      "eval_samples_per_second": 351.097,
+      "eval_steps_per_second": 10.984,
+      "step": 4920
+    },
+    {
+      "epoch": 4.065040650406504,
+      "grad_norm": 3.315011739730835,
+      "learning_rate": 5.609756097560976e-06,
+      "loss": 0.0519,
+      "step": 5000
+    },
+    {
+      "epoch": 4.471544715447155,
+      "grad_norm": 15.6904878616333,
+      "learning_rate": 3.1707317073170736e-06,
+      "loss": 0.0328,
+      "step": 5500
+    },
+    {
+      "epoch": 4.878048780487805,
+      "grad_norm": 15.453346252441406,
+      "learning_rate": 7.317073170731708e-07,
+      "loss": 0.0358,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9273080462120438,
+      "eval_f1": 0.9227413256853779,
+      "eval_f1_medical": 0.9415247964470762,
+      "eval_f1_non_medical": 0.9039578549236796,
+      "eval_loss": 0.3629767894744873,
+      "eval_precision": 0.9229432788139431,
+      "eval_recall": 0.9225412244408466,
+      "eval_runtime": 27.7955,
+      "eval_samples_per_second": 351.891,
+      "eval_steps_per_second": 11.009,
+      "step": 6150
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3125933204124032e+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:cd61ceeb5b5488c255c5b8d354e64b2398c1353b45f7b8e9c22c4da57b97030c
+size 5176