alenatz/cause-biobert-biocause

README.md

@@ -0,0 +1,75 @@
+---
+base_model: dmis-lab/biobert-base-cased-v1.2
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: cause-biobert-biocause
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# cause-biobert-biocause
+
+This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5157
+- Precision: 0.2230
+- Recall: 0.4277
+- F1: 0.2931
+- Accuracy: 0.8241
+- Cause P: 0.2230
+- Cause R: 0.4277
+- Cause F1: 0.2931
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy | Cause P | Cause R | Cause F1 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:-------:|:--------:|
+| 0.6993        | 0.25  | 20   | 0.6314          | 0.0556    | 0.1698 | 0.0837 | 0.7587   | 0.0556  | 0.1698  | 0.0837   |
+| 0.6993        | 0.5   | 40   | 0.5747          | 0.0826    | 0.2327 | 0.1219 | 0.6524   | 0.0826  | 0.2327  | 0.1219   |
+| 0.6993        | 0.75  | 60   | 0.4896          | 0.1086    | 0.3899 | 0.1699 | 0.7420   | 0.1086  | 0.3899  | 0.1699   |
+| 0.6993        | 1.0   | 80   | 0.4554          | 0.1497    | 0.3145 | 0.2028 | 0.7840   | 0.1497  | 0.3145  | 0.2028   |
+| 0.6993        | 1.25  | 100  | 0.4952          | 0.1980    | 0.3774 | 0.2597 | 0.8353   | 0.1980  | 0.3774  | 0.2597   |
+| 0.6993        | 1.5   | 120  | 0.4837          | 0.1749    | 0.3774 | 0.2390 | 0.7984   | 0.1749  | 0.3774  | 0.2390   |
+| 0.6993        | 1.75  | 140  | 0.4786          | 0.1873    | 0.4088 | 0.2569 | 0.7991   | 0.1873  | 0.4088  | 0.2569   |
+| 0.6993        | 2.0   | 160  | 0.5157          | 0.2230    | 0.4277 | 0.2931 | 0.8241   | 0.2230  | 0.4277  | 0.2931   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.3.1.post100
+- Datasets 2.20.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
+  "architectures": [
+    "BertForUnbalancedTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-CAU"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-CAU": 1,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c755fcb09586ae871e1a02f171a50450ff7d84d3ca11754b46171811f07d9a
+size 433270744

runs/Jul12_21-03-26_ccoon/events.out.tfevents.1720811009.ccoon.6644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cac1a2813c406952d19c411133a23cebbd36975ac900736118ed7172a7b3f07
+size 5200

runs/Jul12_21-04-52_ccoon/events.out.tfevents.1720811094.ccoon.6644.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab6823a468dd4ef42fc2f4950712b6753a0418c71b716d88fd2b23b5b4cb7f2
+size 4586

runs/Jul12_21-08-54_ccoon/events.out.tfevents.1720811334.ccoon.7185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca95f12873b2b2017fad1427af3b8e797c4d14725bd4d8cf697d42a26c7677c8
+size 9876

runs/Jul12_21-08-54_ccoon/events.out.tfevents.1720811900.ccoon.7185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ced48948a17662fa4de2582b5d5ff35c3e5329c5a8b4f15e13d9bc20a563eb
+size 1340

runs/Jul12_21-20-42_ccoon/events.out.tfevents.1720812043.ccoon.7539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974e7d1deac93b901ec77ba1e164124933a0203fc37b9c01452c4968c2bc470e
+size 9876

runs/Jul12_21-20-42_ccoon/events.out.tfevents.1720812606.ccoon.7539.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6c610ca24cae78e7ebe15a98040ffcb0fa7b99a9e8cbbc595d88e06f703026
+size 714

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": 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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a755832214ec96c767914859e54d886c33cee24d23b6eaded9ba914025fe95a
+size 4664