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: 0.7662
- Accuracy: 0.8872
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 |
|---|---|---|---|---|
| 1.2847 | 0.0029 | 500 | 0.6642 | 0.8478 |
| 0.6806 | 0.0057 | 1000 | 0.7300 | 0.8827 |
| 0.5189 | 0.0086 | 1500 | 0.7124 | 0.8809 |
| 0.6228 | 0.0114 | 2000 | 0.7662 | 0.8872 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu126
- Datasets 3.3.2
- Tokenizers 0.21.0