metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Qwen2.5-Coder-1.5B-Instruct-Airscript
results: []
Qwen2.5-Coder-1.5B-Instruct-Airscript
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4578
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: 0.0005
- 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: 30
- training_steps: 1599
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1783 | 0.0625 | 100 | 2.1005 |
| 1.8424 | 0.1251 | 200 | 1.8531 |
| 1.7342 | 0.1876 | 300 | 1.7347 |
| 1.6314 | 0.2502 | 400 | 1.6523 |
| 1.5815 | 0.3127 | 500 | 1.5977 |
| 1.5495 | 0.3752 | 600 | 1.5601 |
| 1.5015 | 0.4378 | 700 | 1.5319 |
| 1.4848 | 0.5003 | 800 | 1.5099 |
| 1.4606 | 0.5629 | 900 | 1.4929 |
| 1.4478 | 0.6254 | 1000 | 1.4813 |
| 1.4428 | 0.6879 | 1100 | 1.4717 |
| 1.4248 | 0.7505 | 1200 | 1.4657 |
| 1.4218 | 0.8130 | 1300 | 1.4614 |
| 1.418 | 0.8755 | 1400 | 1.4588 |
| 1.4238 | 0.9381 | 1500 | 1.4578 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.0
- Datasets 3.0.1
- Tokenizers 0.20.1