SIRIS-Lab/geordie-ner

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-base-multilingual-cased-finetuned-geordie
+ 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. -->
+
+# distilbert-base-multilingual-cased-finetuned-geordie
+
+This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0262
+- Precision: 0.9029
+- Recall: 0.9162
+- F1: 0.9095
+- Accuracy: 0.9933
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.022 | 1.0 | 10080 | 0.0205 | 0.8689 | 0.9270 | 0.8970 | 0.9927 |
+| 0.0156 | 2.0 | 20160 | 0.0203 | 0.9034 | 0.9072 | 0.9053 | 0.9930 |
+| 0.0106 | 3.0 | 30240 | 0.0223 | 0.9010 | 0.9157 | 0.9083 | 0.9932 |
+| 0.0082 | 4.0 | 40320 | 0.0262 | 0.9029 | 0.9162 | 0.9095 | 0.9933 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+ "activation": "gelu",
+ "architectures": [
+ "DistilBertForTokenClassification"
+ ],
+ "attention_dropout": 0.1,
+ "dim": 768,
+ "dropout": 0.1,
+ "hidden_dim": 3072,
+ "id2label": {
+ "0": "O",
+ "1": "B-geo",
+ "2": "I-geo"
+ },
+ "initializer_range": 0.02,
+ "label2id": {
+ "B-geo": 1,
+ "I-geo": 2,
+ "O": 0
+ },
+ "max_position_embeddings": 512,
+ "model_type": "distilbert",
+ "n_heads": 12,
+ "n_layers": 6,
+ "output_past": true,
+ "pad_token_id": 0,
+ "qa_dropout": 0.1,
+ "seq_classif_dropout": 0.2,
+ "sinusoidal_pos_embds": false,
+ "tie_weights_": true,
+ "torch_dtype": "float32",
+ "transformers_version": "4.44.2",
+ "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4627472c53078e21cecd3c89b41dc6d6f5f7e8a0a48fd002d8422e128f0e870b
+size 538957900

runs/Oct07_14-39-02_2b433d3cc906/events.out.tfevents.1728312015.2b433d3cc906.1174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e43bff2abaca853422a4c4f62224fbdab0b37611261a26d585790ba267e00b
+size 5499

runs/Oct07_14-41-39_2b433d3cc906/events.out.tfevents.1728312127.2b433d3cc906.1174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960deb28029364e2f90d0702e701c7d842cb0ed8204c60807c088ed1415047ad
+size 24424

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": "DistilBertTokenizer",
+ "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c890e3be4c6f8db2a4cafb5b55c9d654c219b9d733e4841da293a9ede5b838c
+size 5240