alenatz/cause-bert-biocause

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: cause-bert-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-bert-biocause
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4364
+- Precision: 0.1647
+- Recall: 0.3459
+- F1: 0.2231
+- Accuracy: 0.8160
+- Cause P: 0.1647
+- Cause R: 0.3459
+- Cause F1: 0.2231
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------:|:-------:|:--------:|
+| 0.6498 | 0.25 | 20 | 0.6248 | 0.0544 | 0.1698 | 0.0824 | 0.7705 | 0.0544 | 0.1698 | 0.0824 |
+| 0.6498 | 0.5 | 40 | 0.5229 | 0.0532 | 0.1572 | 0.0795 | 0.6600 | 0.0532 | 0.1572 | 0.0795 |
+| 0.6498 | 0.75 | 60 | 0.4613 | 0.1190 | 0.2327 | 0.1574 | 0.8274 | 0.1190 | 0.2327 | 0.1574 |
+| 0.6498 | 1.0 | 80 | 0.4376 | 0.1460 | 0.2956 | 0.1954 | 0.8145 | 0.1460 | 0.2956 | 0.1954 |
+| 0.6498 | 1.25 | 100 | 0.4660 | 0.1829 | 0.2956 | 0.2260 | 0.8312 | 0.1829 | 0.2956 | 0.2260 |
+| 0.6498 | 1.5 | 120 | 0.4523 | 0.1902 | 0.3899 | 0.2557 | 0.8148 | 0.1902 | 0.3899 | 0.2557 |
+| 0.6498 | 1.75 | 140 | 0.4414 | 0.1756 | 0.3711 | 0.2384 | 0.8138 | 0.1756 | 0.3711 | 0.2384 |
+| 0.6498 | 2.0 | 160 | 0.4364 | 0.1647 | 0.3459 | 0.2231 | 0.8160 | 0.1647 | 0.3459 | 0.2231 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.3.1.post100
+- Datasets 2.20.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,34 @@
+{
+ "_name_or_path": "bert-base-cased",
+ "architectures": [
+ "BertForUnbalancedTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "gradient_checkpointing": false,
+ "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:caf1046adc6fb2a1ae9edb53cb7baeb141560b9a7b9e380bf0e2dfc48380e847
+size 433270744

runs/Jul12_17-59-40_ccoon/events.out.tfevents.1720799983.ccoon.637496.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493ecd83246313379605f5f9afe8739b960ac701dd9467a5708ab2eeb5dc7334
+size 4595

runs/Jul12_18-00-10_ccoon/events.out.tfevents.1720800013.ccoon.637496.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbfa2c68da2b37c943e722b3814f975a06ab8b99c29794897ca7b0b9255f6152
+size 9885

runs/Jul12_18-00-10_ccoon/events.out.tfevents.1720800986.ccoon.637496.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cc87731b38776df906d494a8d138fcdee9cfd5bcc76120d8333f98cac90588
+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 +1,55 @@
+{
+ "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_lower_case": false,
+ "mask_token": "[MASK]",
+ "model_max_length": 512,
+ "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 sha256:6ba01b0c0777fb95fd9711cb48caba501e373b4277b5162c897a522452296ade
+size 4664