property-query-analyzer
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 607417.25
- Property Type Accuracy: 0.102
- Config F1: 0.0
- Price Min Mse: 117061.2812
- Price Max Mse: 490353.2188
- Location F1: 0.0
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 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: 1000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Property Type Accuracy | Config F1 | Price Min Mse | Price Max Mse | Location F1 |
|---|---|---|---|---|---|---|---|---|
| 690858.96 | 1.0 | 625 | 670975.25 | 0.102 | 0.0 | 138166.9688 | 532805.4375 | 0.0 |
| 662804.68 | 2.0 | 1250 | 643823.75 | 0.118 | 0.0 | 128886.1406 | 514934.875 | 0.0 |
| 624329.52 | 3.0 | 1875 | 622994.5625 | 0.102 | 0.0 | 122034.8828 | 500957.0 | 0.0 |
| 572816.72 | 4.0 | 2500 | 611227.75 | 0.074 | 0.0 | 118267.9297 | 492957.0938 | 0.0 |
| 634617.56 | 5.0 | 3125 | 607417.25 | 0.102 | 0.0 | 117061.2812 | 490353.2188 | 0.0 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 10
Model tree for hsharma1996/property-query-analyzer
Base model
google-bert/bert-base-uncased