fabiopassos/bertimbau-base-misobr

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+license: mit
+base_model: neuralmind/bert-base-portuguese-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: results_bertimbau_base
+  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. -->
+
+# results_bertimbau_base
+
+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: 1.4087
+- Accuracy: 0.7889
+- F1 Macro: 0.7872
+- Precision Macro: 0.7983
+- Recall Macro: 0.7889
+- F1 Positive: 0.7683
+- Precision Positive: 0.8514
+- Recall Positive: 0.7
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | F1 Positive | Precision Positive | Recall Positive |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------------:|:------------:|:-----------:|:------------------:|:---------------:|
+| No log        | 1.0   | 45   | 0.6900          | 0.5111   | 0.4117   | 0.5343          | 0.5111       | 0.6535      | 0.5061             | 0.9222          |
+| 0.6977        | 2.0   | 90   | 0.6337          | 0.6722   | 0.6710   | 0.6748          | 0.6722       | 0.6509      | 0.6962             | 0.6111          |
+| 0.648         | 3.0   | 135  | 0.5049          | 0.7667   | 0.7648   | 0.7754          | 0.7667       | 0.7439      | 0.8243             | 0.6778          |
+| 0.509         | 4.0   | 180  | 0.4051          | 0.8056   | 0.8055   | 0.8056          | 0.8056       | 0.8045      | 0.8090             | 0.8             |
+| 0.3076        | 5.0   | 225  | 0.4363          | 0.7833   | 0.7833   | 0.7836          | 0.7833       | 0.7869      | 0.7742             | 0.8             |
+| 0.1829        | 6.0   | 270  | 1.0173          | 0.7389   | 0.7260   | 0.7941          | 0.7389       | 0.6667      | 0.9216             | 0.5222          |
+| 0.164         | 7.0   | 315  | 0.7491          | 0.8333   | 0.8330   | 0.8360          | 0.8333       | 0.8404      | 0.8061             | 0.8778          |
+| 0.0398        | 8.0   | 360  | 0.8190          | 0.8278   | 0.8275   | 0.8298          | 0.8278       | 0.8208      | 0.8554             | 0.7889          |
+| 0.0507        | 9.0   | 405  | 0.9708          | 0.8222   | 0.8219   | 0.8248          | 0.8222       | 0.8140      | 0.8537             | 0.7778          |
+| 0.0531        | 10.0  | 450  | 0.9090          | 0.8333   | 0.8331   | 0.8348          | 0.8333       | 0.8276      | 0.8571             | 0.8             |
+| 0.0531        | 11.0  | 495  | 1.1804          | 0.8222   | 0.8219   | 0.8248          | 0.8222       | 0.8140      | 0.8537             | 0.7778          |
+| 0.0268        | 12.0  | 540  | 1.1690          | 0.8222   | 0.8217   | 0.8263          | 0.8222       | 0.8118      | 0.8625             | 0.7667          |
+| 0.0259        | 13.0  | 585  | 1.2368          | 0.8333   | 0.8333   | 0.8335          | 0.8333       | 0.8315      | 0.8409             | 0.8222          |
+| 0.0253        | 14.0  | 630  | 1.2803          | 0.8056   | 0.8055   | 0.8059          | 0.8056       | 0.8023      | 0.8161             | 0.7889          |
+| 0.0263        | 15.0  | 675  | 1.3243          | 0.8167   | 0.8162   | 0.8199          | 0.8167       | 0.8070      | 0.8519             | 0.7667          |
+| 0.0093        | 16.0  | 720  | 1.4087          | 0.7889   | 0.7872   | 0.7983          | 0.7889       | 0.7683      | 0.8514             | 0.7             |
+
+
+### Framework versions
+
+- Transformers 4.57.0
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.57.0",
+  "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:ce6b4c65dd5f93a15151a549499a56fb14975c2dcd60483e54b9d1be6f3a3406
+size 435722224

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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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:fe238c26977d25200ad92dda28112bf05d182f6e26cbddc3805b87a15b64e940
+size 5777