syubraj/espanyol_bert_based_ner

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+model-index:
+- name: fine_tune_bert_output
+  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. -->
+
+# fine_tune_bert_output
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3320
+- Overall Precision: 0.9051
+- Overall Recall: 0.9121
+- Overall F1: 0.9086
+- Overall Accuracy: 0.9577
+- Loc F1: 0.9190
+- Org F1: 0.8663
+- Per F1: 0.9367
+
+## 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: 16
+- eval_batch_size: 16
+- 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 | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Loc F1 | Org F1 | Per F1 |
+|:-------------:|:-----:|:-----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:------:|:------:|:------:|
+| 0.2713        | 0.8   | 1000  | 0.2236          | 0.8498            | 0.8672         | 0.8584     | 0.9401           | 0.8834 | 0.8019 | 0.8790 |
+| 0.1537        | 1.6   | 2000  | 0.1909          | 0.8772            | 0.8943         | 0.8857     | 0.9495           | 0.9002 | 0.8369 | 0.9164 |
+| 0.1152        | 2.4   | 3000  | 0.2095          | 0.8848            | 0.8981         | 0.8914     | 0.9523           | 0.9039 | 0.8432 | 0.9220 |
+| 0.0889        | 3.2   | 4000  | 0.2223          | 0.8978            | 0.8998         | 0.8988     | 0.9546           | 0.9080 | 0.8569 | 0.9290 |
+| 0.0701        | 4.0   | 5000  | 0.2152          | 0.8937            | 0.9042         | 0.8989     | 0.9544           | 0.9113 | 0.8565 | 0.9246 |
+| 0.0457        | 4.8   | 6000  | 0.2365          | 0.9017            | 0.9069         | 0.9043     | 0.9563           | 0.9164 | 0.8616 | 0.9310 |
+| 0.0364        | 5.6   | 7000  | 0.2622          | 0.9037            | 0.9086         | 0.9061     | 0.9578           | 0.9148 | 0.8639 | 0.9365 |
+| 0.026         | 6.4   | 8000  | 0.2916          | 0.9037            | 0.9159         | 0.9097     | 0.9585           | 0.9183 | 0.8712 | 0.9366 |
+| 0.0215        | 7.2   | 9000  | 0.2985          | 0.9022            | 0.9128         | 0.9074     | 0.9565           | 0.9178 | 0.8676 | 0.9323 |
+| 0.0134        | 8.0   | 10000 | 0.3071          | 0.904             | 0.9131         | 0.9085     | 0.9574           | 0.9198 | 0.8671 | 0.9344 |
+| 0.0091        | 8.8   | 11000 | 0.3335          | 0.9056            | 0.9115         | 0.9085     | 0.9573           | 0.9175 | 0.8670 | 0.9373 |
+| 0.0074        | 9.6   | 12000 | 0.3320          | 0.9051            | 0.9121         | 0.9086     | 0.9577           | 0.9190 | 0.8663 | 0.9367 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8760bc02c4f3d72b7d8e4a6f2091dbef75086c765584b859b58e37562131a699
+size 709096284

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 sha256:4792ed0f8576f2abb4c31d6e9c96da8fd870970b4825c9d4121b0ce4207f99e8
+size 5240