metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
- generated_from_trainer
model-index:
- name: qwen_checkpoints
results: []
qwen_checkpoints
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0716
- Mse: 0.0716
- Mae: 0.2183
- R Squared: 0.2014
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R Squared |
|---|---|---|---|---|---|---|
| 0.0856 | 0.1558 | 100 | 0.0878 | 0.0878 | 0.2351 | 0.0207 |
| 0.0843 | 0.3115 | 200 | 0.0803 | 0.0803 | 0.2314 | 0.1045 |
| 0.0851 | 0.4673 | 300 | 0.0882 | 0.0882 | 0.2278 | 0.0168 |
| 0.0676 | 0.6231 | 400 | 0.0716 | 0.0716 | 0.2183 | 0.2014 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3