metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2-1.5B
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: gating_network_qwen
results: []
gating_network_qwen
This model is a fine-tuned version of Qwen/Qwen2-1.5B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1874
- Accuracy: 0.9548
- F1: 0.9526
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: 32
- eval_batch_size: 32
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.673 | 0.0111 | 100 | 0.2750 | 0.9185 | 0.9178 |
| 0.2584 | 0.0223 | 200 | 0.2737 | 0.9353 | 0.9321 |
| 0.2229 | 0.0334 | 300 | 0.1795 | 0.9597 | 0.9590 |
| 0.2101 | 0.0446 | 400 | 0.1874 | 0.9548 | 0.9526 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0