oracle-corejur/bert_oracle_class_final_dataset_vert_v2

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: neuralmind/bert-base-portuguese-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+- f1
+model-index:
+- name: oracle_class_vert_v3
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/generation_jur/oracle_text_classification/runs/fi2ble5z)
+# oracle_class_vert_v3
+
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5665
+- Precision: 0.8326
+- Recall: 0.8336
+- Accuracy: 0.8477
+- F1: 0.8310
+
+## 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: 6e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
+| 0.5484        | 1.4589 | 550  | 0.5911          | 0.8063    | 0.8028 | 0.8308   | 0.8010 |
+| 0.3253        | 2.9178 | 1100 | 0.5665          | 0.8326    | 0.8336 | 0.8477   | 0.8310 |
+
+
+### Framework versions
+
+- Transformers 4.43.1
+- Pytorch 2.2.0
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "APLICATIVOS",
+    "1": "ARMAZENAMENTO",
+    "2": "BACKUP",
+    "3": "BANCO DE DADOS",
+    "4": "CLOUD",
+    "5": "DATACENTER",
+    "6": "HARDWARE SERVIDOR",
+    "7": "HIPERCONVERGENCIA",
+    "8": "IA",
+    "9": "VIRTUALIZACAO"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "APLICATIVOS": 0,
+    "ARMAZENAMENTO": 1,
+    "BACKUP": 2,
+    "BANCO DE DADOS": 3,
+    "CLOUD": 4,
+    "DATACENTER": 5,
+    "HARDWARE SERVIDOR": 6,
+    "HIPERCONVERGENCIA": 7,
+    "IA": 8,
+    "VIRTUALIZACAO": 9
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "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 sha256:2966f2ab86ced92449b2235204f5afdfd73469e481aa4ecfd12c1ae24b2f0c12
+size 435746832

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 +1,59 @@
+{
+  "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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "padding": "max_length",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c83e6397b11a8e5820e6a1b3cf80be2d99793aa6cbfca637f65332dbfe3361b6
+size 5240