metadata
library_name: transformers
license: other
base_model: Qwen/Qwen1.5-32B
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fine_tuned_per_domain_balanced_32B
results: []
fine_tuned_per_domain_balanced_32B
This model is a fine-tuned version of Qwen/Qwen1.5-32B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7888
- Accuracy: 0.8908
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-06
- train_batch_size: 1
- eval_batch_size: 1
- 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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8972 | 0.0029 | 500 | 1.5903 | 0.7475 |
| 2.0489 | 0.0057 | 1000 | 1.1390 | 0.8111 |
| 1.2974 | 0.0086 | 1500 | 1.2533 | 0.8057 |
| 1.3929 | 0.0114 | 2000 | 1.3143 | 0.8156 |
| 0.5961 | 0.0143 | 2500 | 1.0441 | 0.8451 |
| 0.4478 | 0.0172 | 3000 | 1.0491 | 0.8496 |
| 1.3262 | 0.0200 | 3500 | 1.0400 | 0.8478 |
| 0.9755 | 0.0229 | 4000 | 0.9457 | 0.8621 |
| 0.7849 | 0.0258 | 4500 | 0.8249 | 0.8684 |
| 0.7091 | 0.0286 | 5000 | 0.7580 | 0.8836 |
| 0.527 | 0.0315 | 5500 | 0.8654 | 0.8756 |
| 0.8061 | 0.0343 | 6000 | 0.8890 | 0.8782 |
| 0.1774 | 0.0372 | 6500 | 0.7888 | 0.8908 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0