metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- llama-factory
- generated_from_trainer
model-index:
- name: Models_Ouput2
results: []
Models_Ouput2
This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3767
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2862 | 0.0166 | 100 | 1.2021 |
| 1.0539 | 0.0331 | 200 | 1.0201 |
| 0.495 | 1.0 | 6040 | 0.4768 |
| 0.3633 | 2.0 | 12080 | 0.3888 |
| 0.2837 | 3.0 | 18120 | 0.3767 |
Framework versions
- PEFT 0.15.1
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1