Training in progress, epoch 1

README.md

@@ -0,0 +1,105 @@
+---
+license: mit
+base_model: neuralmind/bert-base-portuguese-cased
+tags:
+- generated_from_trainer
+datasets:
+- harem
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: harem-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: harem
+      type: harem
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6869415807560137
+    - name: Recall
+      type: recall
+      value: 0.7467314157639149
+    - name: F1
+      type: f1
+      value: 0.7155897619473779
+    - name: Accuracy
+      type: accuracy
+      value: 0.9527588964414234
+---
+
+<!-- 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. -->
+
+# harem-ner
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the harem dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2411
+- Precision: 0.6869
+- Recall: 0.7467
+- F1: 0.7156
+- Accuracy: 0.9528
+
+## 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: 300
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 16   | 0.7683          | 0.0       | 0.0    | 0.0    | 0.8358   |
+| No log        | 2.0   | 32   | 0.4727          | 0.3375    | 0.2955 | 0.3151 | 0.8803   |
+| No log        | 3.0   | 48   | 0.3498          | 0.4859    | 0.4838 | 0.4848 | 0.9090   |
+| No log        | 4.0   | 64   | 0.2771          | 0.5651    | 0.6223 | 0.5924 | 0.9354   |
+| No log        | 5.0   | 80   | 0.2309          | 0.5901    | 0.6743 | 0.6294 | 0.9424   |
+| No log        | 6.0   | 96   | 0.2195          | 0.6229    | 0.6997 | 0.6590 | 0.9469   |
+| No log        | 7.0   | 112  | 0.2151          | 0.6239    | 0.6903 | 0.6554 | 0.9480   |
+| No log        | 8.0   | 128  | 0.2178          | 0.6682    | 0.7236 | 0.6948 | 0.9504   |
+| No log        | 9.0   | 144  | 0.2210          | 0.6808    | 0.7426 | 0.7104 | 0.9514   |
+| No log        | 10.0  | 160  | 0.2292          | 0.6863    | 0.7348 | 0.7097 | 0.9512   |
+| No log        | 11.0  | 176  | 0.2312          | 0.6932    | 0.7452 | 0.7183 | 0.9522   |
+| No log        | 12.0  | 192  | 0.2258          | 0.6966    | 0.7523 | 0.7234 | 0.9535   |
+| No log        | 13.0  | 208  | 0.2337          | 0.7076    | 0.7557 | 0.7309 | 0.9537   |
+| No log        | 14.0  | 224  | 0.2299          | 0.6907    | 0.7549 | 0.7214 | 0.9533   |
+| No log        | 15.0  | 240  | 0.2381          | 0.6980    | 0.7553 | 0.7255 | 0.9524   |
+| No log        | 16.0  | 256  | 0.2411          | 0.6869    | 0.7467 | 0.7156 | 0.9528   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-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": "O",
+    "1": "B-PESSOA",
+    "2": "I-PESSOA",
+    "3": "B-ORGANIZACAO",
+    "4": "I-ORGANIZACAO",
+    "5": "B-LOCAL",
+    "6": "I-LOCAL",
+    "7": "B-TEMPO",
+    "8": "I-TEMPO",
+    "9": "B-VALOR",
+    "10": "I-VALOR",
+    "11": "B-ABSTRACCAO",
+    "12": "I-ABSTRACCAO",
+    "13": "B-ACONTECIMENTO",
+    "14": "I-ACONTECIMENTO",
+    "15": "B-COISA",
+    "16": "I-COISA",
+    "17": "B-OBRA",
+    "18": "I-OBRA",
+    "19": "B-OUTRO",
+    "20": "I-OUTRO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ABSTRACCAO": 11,
+    "B-ACONTECIMENTO": 13,
+    "B-COISA": 15,
+    "B-LOCAL": 5,
+    "B-OBRA": 17,
+    "B-ORGANIZACAO": 3,
+    "B-OUTRO": 19,
+    "B-PESSOA": 1,
+    "B-TEMPO": 7,
+    "B-VALOR": 9,
+    "I-ABSTRACCAO": 12,
+    "I-ACONTECIMENTO": 14,
+    "I-COISA": 16,
+    "I-LOCAL": 6,
+    "I-OBRA": 18,
+    "I-ORGANIZACAO": 4,
+    "I-OUTRO": 20,
+    "I-PESSOA": 2,
+    "I-TEMPO": 8,
+    "I-VALOR": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36b6497d10e1c745aaff1695cd9799caa8d2c7bff9fe9bd2d56f70fe5f18446
+size 433418116

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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35c8a83ba212542ab845af537b2dc66aa46f719902cfa0d451d08c33f1230e48
+size 4984