metadata
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2-1.5B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_hswag
results: []
fine_tuned_hswag
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: 0.6744
- Accuracy: 0.7498
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5837 | 0.0322 | 100 | 0.4305 | 0.8946 |
| 0.4321 | 0.0644 | 200 | 0.3573 | 0.9167 |
| 0.3123 | 0.0966 | 300 | 0.7352 | 0.8979 |
| 0.2957 | 0.1287 | 400 | 0.2162 | 0.9153 |
| 0.234 | 0.1609 | 500 | 0.2174 | 0.9450 |
| 0.1454 | 0.1931 | 600 | 0.1396 | 0.9587 |
| 0.265 | 0.2253 | 700 | 0.1031 | 0.9526 |
| 0.1734 | 0.2575 | 800 | 0.1756 | 0.9569 |
| 0.1896 | 0.2897 | 900 | 0.1828 | 0.9591 |
| 0.1723 | 0.3219 | 1000 | 0.6744 | 0.7498 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0