ai-research-lab/bert-question-classifier

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- recall
+- precision
+- f1
+model-index:
+- name: bert-question-classifier
+  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. -->
+
+# bert-question-classifier
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9599
+- Accuracy: 0.9332
+- Recall: 0.8139
+- Precision: 0.8199
+- F1: 0.8169
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 390  | 1.9599          | 0.9332   | 0.8139 | 0.8199    | 0.8169 |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,180 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "d",
+    "1": "y",
+    "2": "c",
+    "3": "o",
+    "4": "career",
+    "5": "family",
+    "6": "marriage",
+    "7": "love",
+    "8": "self",
+    "9": "education",
+    "10": "wealth",
+    "11": "business",
+    "12": "hard times",
+    "13": "health",
+    "14": "spirituality",
+    "15": "others",
+    "16": "time_based",
+    "17": "positive_perception"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "business": 11,
+    "c": 2,
+    "career": 4,
+    "d": 0,
+    "education": 9,
+    "family": 5,
+    "hard times": 12,
+    "health": 13,
+    "love": 7,
+    "marriage": 6,
+    "o": 3,
+    "others": 15,
+    "positive_perception": 17,
+    "self": 8,
+    "spirituality": 14,
+    "time_based": 16,
+    "wealth": 10,
+    "y": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "task_specific_params": {
+    "classifier_config": {
+      "multi_class": [
+        {
+          "column": "question type",
+          "labels": [
+            [
+              "d",
+              "Descriptive"
+            ],
+            [
+              "y",
+              "Yes/No"
+            ],
+            [
+              "c",
+              "Complex"
+            ],
+            [
+              "o",
+              "Options"
+            ]
+          ],
+          "loss_weight": 1,
+          "name": "type"
+        },
+        {
+          "column": "category",
+          "labels": [
+            [
+              "career",
+              "Career"
+            ],
+            [
+              "family",
+              "Family"
+            ],
+            [
+              "marriage",
+              "Marriage"
+            ],
+            [
+              "love",
+              "Love"
+            ],
+            [
+              "self",
+              "Self"
+            ],
+            [
+              "education",
+              "Education"
+            ],
+            [
+              "wealth",
+              "Wealth"
+            ],
+            [
+              "business",
+              "Business"
+            ],
+            [
+              "hard times",
+              "Hard Times"
+            ],
+            [
+              "health",
+              "Health"
+            ],
+            [
+              "spirituality",
+              "Spirituality"
+            ],
+            [
+              "others",
+              "Others"
+            ]
+          ],
+          "loss_weight": 1,
+          "name": "category"
+        }
+      ],
+      "multi_label": [
+        {
+          "columns": {
+            "perception": {
+              "n": 0,
+              "p": 1,
+              "y": 1
+            },
+            "time based": {
+              "n": 0,
+              "p": 1,
+              "y": 1
+            }
+          },
+          "labels": [
+            [
+              "time_based",
+              "Time Based"
+            ],
+            [
+              "positive_perception",
+              "Positive Perception"
+            ]
+          ],
+          "loss_weight": 1,
+          "name": "attributes",
+          "threshold": 0
+        }
+      ]
+    },
+    "random": "marimo notebook run 1"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918408f849c0cf877a7848a1a75c08f56b4d17e6b120286d01058d04595c1cc0
+size 438007864

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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "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 sha256:3e6e4febefdcf1abcdc88065ebac690bee3db2bb7fc5aafa5d82952e12cd68b1
+size 5368