metadata
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-3B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: web_policy_sft
results: []
web_policy_sft
This model is a fine-tuned version of /data/hzy/models--Qwen--Qwen2.5-3B-Instruct/snapshots/aa8e72537993ba99e69dfaafa59ed015b17504d1 on the web_policy_sft dataset. It achieves the following results on the evaluation set:
- Loss: 0.1625
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- total_eval_batch_size: 2
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5121 | 0.0470 | 50 | 0.4876 |
| 0.4615 | 0.0940 | 100 | 0.3849 |
| 0.37 | 0.1409 | 150 | 0.3281 |
| 0.3749 | 0.1879 | 200 | 0.2892 |
| 0.2863 | 0.2349 | 250 | 0.2757 |
| 0.3078 | 0.2819 | 300 | 0.2549 |
| 0.2921 | 0.3289 | 350 | 0.2316 |
| 0.3191 | 0.3759 | 400 | 0.2353 |
| 0.313 | 0.4228 | 450 | 0.2231 |
| 0.2037 | 0.4698 | 500 | 0.2138 |
| 0.1729 | 0.5168 | 550 | 0.2074 |
| 0.289 | 0.5638 | 600 | 0.1954 |
| 0.2775 | 0.6108 | 650 | 0.1897 |
| 0.1546 | 0.6577 | 700 | 0.1814 |
| 0.1613 | 0.7047 | 750 | 0.1746 |
| 0.0956 | 0.7517 | 800 | 0.1725 |
| 0.1692 | 0.7987 | 850 | 0.1683 |
| 0.1885 | 0.8457 | 900 | 0.1653 |
| 0.2799 | 0.8926 | 950 | 0.1637 |
| 0.1971 | 0.9396 | 1000 | 0.1628 |
| 0.1464 | 0.9866 | 1050 | 0.1626 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1