Model save

README.md

@@ -1,45 +1,71 @@
-
 ---
-language: en
-license: mit
-datasets:
-  - your_dataset_name
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
 tags:
-  - text-classification
-  - bert
-  - query-classification
+- generated_from_trainer
 metrics:
-  - accuracy: 0.9789272030651341
-  - f1: 0.9789776553861008
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: modern-bert-finetuned-query-classification
+  results: []
 ---
 
-# BERT Fine-tuned for Query Classification
+<!-- 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. -->
+
+# modern-bert-finetuned-query-classification
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/answerdotai/ModernBERT-base) on a query classification dataset.
+This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1555
+- Accuracy: 0.9789
+- F1: 0.9790
+- Precision: 0.9792
+- Recall: 0.9789
 
 ## Model description
 
-The model was fine-tuned on queries to classify them into specific categories.
+More information needed
+
+## Intended uses & limitations
+
+More information needed
 
 ## Training and evaluation data
 
-The model was trained on [describe your dataset here].
+More information needed
 
 ## Training procedure
 
-The model was trained with the following hyperparameters:
-- Learning rate: 2e-05
-- Batch size: 8
-- Number of epochs: 5
-- Optimizer: AdamW
-- Weight decay: 0.01
+### Training hyperparameters
 
-## Evaluation results
+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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 305  | 0.2230          | 0.9579   | 0.9579 | 0.9600    | 0.9579 |
+| 0.1385        | 2.0   | 610  | 0.1555          | 0.9789   | 0.9790 | 0.9792    | 0.9789 |
+| 0.1385        | 3.0   | 915  | 0.1744          | 0.9693   | 0.9694 | 0.9701    | 0.9693 |
+| 0.0189        | 4.0   | 1220 | 0.2378          | 0.9674   | 0.9675 | 0.9684    | 0.9674 |
+| 0.0022        | 5.0   | 1525 | 0.2181          | 0.9732   | 0.9733 | 0.9737    | 0.9732 |
 
-The model achieved the following results on the validation set:
-- Accuracy: 0.9789
-- F1 Score: 0.9790
 
-## Uses and limitations
+### Framework versions
 
-[Discuss the intended uses and limitations of your model]
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50283,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,