ai-research-lab/bert-question-classifier

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google-bert/bert-large-uncased
+base_model: google-bert/bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-question-classifier
 
-This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on the None dataset.
+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: 1.0482
-- Accuracy: 0.9685
-- Recall: 0.9174
-- Precision: 0.9111
-- F1: 0.9142
+- Loss: 2.7007
+- Accuracy: 0.9562
+- Recall: 0.7745
+- Precision: 0.7606
+- F1: 0.7675
 
 ## Model description
 
@@ -44,28 +44,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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: 5
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| No log        | 1.0   | 195  | 1.0938          | 0.9641   | 0.9077 | 0.8976    | 0.9026 |
-| No log        | 2.0   | 390  | 0.9270          | 0.9683   | 0.9186 | 0.9091    | 0.9138 |
-| 1.2215        | 3.0   | 585  | 0.9714          | 0.9676   | 0.9155 | 0.9081    | 0.9118 |
-| 1.2215        | 4.0   | 780  | 1.0289          | 0.9678   | 0.9167 | 0.9082    | 0.9124 |
-| 1.2215        | 5.0   | 975  | 1.0482          | 0.9685   | 0.9174 | 0.9111    | 0.9142 |
+| No log        | 1.0   | 390  | 2.7007          | 0.9562   | 0.7745 | 0.7606    | 0.7675 |
 
 
 ### Framework versions
 
-- Transformers 4.47.1
-- Pytorch 2.5.1+cu124
+- Transformers 4.48.1
+- Pytorch 2.5.1
 - Datasets 3.2.0
 - Tokenizers 0.21.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google-bert/bert-large-uncased",
+  "_name_or_path": "google-bert/bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,54 +8,86 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "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"
+    "4": "self",
+    "5": "health",
+    "6": "accumulated wealth",
+    "7": "family",
+    "8": "social media",
+    "9": "short travel",
+    "10": "sports",
+    "11": "property",
+    "12": "primary education",
+    "13": "love",
+    "14": "romance",
+    "15": "children",
+    "16": "higher education",
+    "17": "job",
+    "18": "diseases",
+    "19": "hard times",
+    "20": "competitive exam",
+    "21": "marriage",
+    "22": "business",
+    "23": "life span",
+    "24": "unearned wealth",
+    "25": "spirituality",
+    "26": "highest education",
+    "27": "long travel",
+    "28": "career",
+    "29": "income",
+    "30": "foreign",
+    "31": "expense",
+    "32": "time_based",
+    "33": "positive_perception"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
-    "business": 11,
+    "accumulated wealth": 6,
+    "business": 22,
     "c": 2,
-    "career": 4,
+    "career": 28,
+    "children": 15,
+    "competitive exam": 20,
     "d": 0,
-    "education": 9,
-    "family": 5,
-    "hard times": 12,
-    "health": 13,
-    "love": 7,
-    "marriage": 6,
+    "diseases": 18,
+    "expense": 31,
+    "family": 7,
+    "foreign": 30,
+    "hard times": 19,
+    "health": 5,
+    "higher education": 16,
+    "highest education": 26,
+    "income": 29,
+    "job": 17,
+    "life span": 23,
+    "long travel": 27,
+    "love": 13,
+    "marriage": 21,
     "o": 3,
-    "others": 15,
-    "positive_perception": 17,
-    "self": 8,
-    "spirituality": 14,
-    "time_based": 16,
-    "wealth": 10,
+    "positive_perception": 33,
+    "primary education": 12,
+    "property": 11,
+    "romance": 14,
+    "self": 4,
+    "short travel": 9,
+    "social media": 8,
+    "spirituality": 25,
+    "sports": 10,
+    "time_based": 32,
+    "unearned wealth": 24,
     "y": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "task_specific_params": {
@@ -88,52 +120,116 @@
           "column": "category",
           "labels": [
             [
-              "career",
-              "Career"
+              "self",
+              "Self"
+            ],
+            [
+              "health",
+              "Health"
+            ],
+            [
+              "accumulated wealth",
+              "Accumulated Wealth"
             ],
             [
               "family",
               "Family"
             ],
             [
-              "marriage",
-              "Marriage"
+              "social media",
+              "Social media"
+            ],
+            [
+              "short travel",
+              "Short Travel"
+            ],
+            [
+              "sports",
+              "Sports"
+            ],
+            [
+              "property",
+              "Property"
+            ],
+            [
+              "primary education",
+              "Primary Education"
             ],
             [
               "love",
               "Love"
             ],
             [
-              "self",
-              "Self"
+              "romance",
+              "Romance"
             ],
             [
-              "education",
-              "Education"
+              "children",
+              "Children"
             ],
             [
-              "wealth",
-              "Wealth"
+              "higher education",
+              "Higher Education"
             ],
             [
-              "business",
-              "Business"
+              "job",
+              "Job"
+            ],
+            [
+              "diseases",
+              "Diseases"
             ],
             [
               "hard times",
               "Hard Times"
             ],
             [
-              "health",
-              "Health"
+              "competitive exam",
+              "Competitive Exam"
+            ],
+            [
+              "marriage",
+              "Marriage"
+            ],
+            [
+              "business",
+              "Business"
+            ],
+            [
+              "life span",
+              "Life Span"
+            ],
+            [
+              "unearned wealth",
+              "Unearned Wealth"
             ],
             [
               "spirituality",
               "Spirituality"
             ],
             [
-              "others",
-              "Others"
+              "highest education",
+              "Highest Education"
+            ],
+            [
+              "long travel",
+              "Long Travel"
+            ],
+            [
+              "career",
+              "Career"
+            ],
+            [
+              "income",
+              "Income"
+            ],
+            [
+              "foreign",
+              "Foreign"
+            ],
+            [
+              "expense",
+              "Expense"
             ]
           ],
           "loss_weight": 1,
@@ -172,7 +268,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e051a25632f562b42b43b39165e0be87a4c26870b9425a1ad001781d0e8424
-size 1340688368
+oid sha256:c77fda2b4c65c07eff0953a86be82328642faa5879226e815f216ed2a530d1cd
+size 438057080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585c7814983dabb3dee43e0fab18f20f272fba6a9eda75c7688766f9b0dfe367
+oid sha256:fe326bedc7e4fe353d3f6f21804bc9d7be5961535ec6135868793cdc746e5fb8
 size 5368