cmi-intent-classifier-v1
This model is a fine-tuned version of xhub/cmi-intent-classifier on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0883
- Accuracy: {'accuracy': 0.9902386117136659}
- Precision: {'precision': 0.9903510498065617}
- F1: {'f1': 0.9902182723563171}
- Recall: {'recall': 0.9902386117136659}
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 231 | 0.0989 | {'accuracy': 0.982646420824295} | {'precision': 0.9830026219988417} | {'f1': 0.9826146119352713} | {'recall': 0.982646420824295} |
| No log | 2.0 | 462 | 0.0713 | {'accuracy': 0.9848156182212582} | {'precision': 0.9848586315054753} | {'f1': 0.9848051991118612} | {'recall': 0.9848156182212582} |
| 0.0556 | 3.0 | 693 | 0.0759 | {'accuracy': 0.9891540130151844} | {'precision': 0.9892928162619692} | {'f1': 0.9891645622565809} | {'recall': 0.9891540130151844} |
| 0.0556 | 4.0 | 924 | 0.0781 | {'accuracy': 0.9880694143167028} | {'precision': 0.9882940651710526} | {'f1': 0.9880558669679527} | {'recall': 0.9880694143167028} |
| 0.01 | 5.0 | 1155 | 0.0952 | {'accuracy': 0.9859002169197397} | {'precision': 0.9860278014567007} | {'f1': 0.9858894411052812} | {'recall': 0.9859002169197397} |
| 0.01 | 6.0 | 1386 | 0.0951 | {'accuracy': 0.9848156182212582} | {'precision': 0.9850183276136155} | {'f1': 0.9847935148784525} | {'recall': 0.9848156182212582} |
| 0.0052 | 7.0 | 1617 | 0.1083 | {'accuracy': 0.982646420824295} | {'precision': 0.9832358024736132} | {'f1': 0.9826372058370486} | {'recall': 0.982646420824295} |
| 0.0052 | 8.0 | 1848 | 0.0894 | {'accuracy': 0.9891540130151844} | {'precision': 0.9892617252983917} | {'f1': 0.9891180233703651} | {'recall': 0.9891540130151844} |
| 0.0015 | 9.0 | 2079 | 0.0829 | {'accuracy': 0.9913232104121475} | {'precision': 0.9914580258788241} | {'f1': 0.9913024714765813} | {'recall': 0.9913232104121475} |
| 0.0015 | 10.0 | 2310 | 0.0775 | {'accuracy': 0.9913232104121475} | {'precision': 0.9914039091193311} | {'f1': 0.9912930173649313} | {'recall': 0.9913232104121475} |
| 0.0015 | 11.0 | 2541 | 0.0857 | {'accuracy': 0.9891540130151844} | {'precision': 0.9892478213519429} | {'f1': 0.9891377567928298} | {'recall': 0.9891540130151844} |
| 0.0015 | 12.0 | 2772 | 0.0868 | {'accuracy': 0.9891540130151844} | {'precision': 0.9892478213519429} | {'f1': 0.9891377567928298} | {'recall': 0.9891540130151844} |
| 0.0001 | 13.0 | 3003 | 0.0873 | {'accuracy': 0.9902386117136659} | {'precision': 0.9903510498065617} | {'f1': 0.9902182723563171} | {'recall': 0.9902386117136659} |
| 0.0001 | 14.0 | 3234 | 0.0877 | {'accuracy': 0.9902386117136659} | {'precision': 0.9903510498065617} | {'f1': 0.9902182723563171} | {'recall': 0.9902386117136659} |
| 0.0001 | 15.0 | 3465 | 0.0881 | {'accuracy': 0.9902386117136659} | {'precision': 0.9903510498065617} | {'f1': 0.9902182723563171} | {'recall': 0.9902386117136659} |
| 0.0001 | 16.0 | 3696 | 0.0883 | {'accuracy': 0.9902386117136659} | {'precision': 0.9903510498065617} | {'f1': 0.9902182723563171} | {'recall': 0.9902386117136659} |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5