qwen-ft
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.6514
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- training_steps: 800
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.7492 | 0.0920 | 50 | 7.5711 |
| 7.4321 | 0.1841 | 100 | 7.3186 |
| 7.0377 | 0.2761 | 150 | 6.9218 |
| 6.8861 | 0.3682 | 200 | 6.7542 |
| 6.7161 | 0.4602 | 250 | 6.5817 |
| 6.4542 | 0.5522 | 300 | 6.3050 |
| 6.3839 | 0.6443 | 350 | 6.2909 |
| 6.1342 | 0.7363 | 400 | 6.0133 |
| 5.9798 | 0.8283 | 450 | 5.8894 |
| 5.9043 | 0.9204 | 500 | 5.8061 |
| 5.889 | 1.0124 | 550 | 5.7376 |
| 5.7778 | 1.1045 | 600 | 5.6900 |
| 5.8077 | 1.1965 | 650 | 5.6643 |
| 5.7363 | 1.2885 | 700 | 5.6539 |
| 5.7524 | 1.3806 | 750 | 5.6515 |
| 5.7289 | 1.4726 | 800 | 5.6514 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.