metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-7B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 57e1d8ef-0d55-4e8b-9048-8c3a434101e4
results: []
57e1d8ef-0d55-4e8b-9048-8c3a434101e4
This model is a fine-tuned version of unsloth/Qwen2-7B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1270
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: 0.00021
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0011 | 1 | 2.6140 |
| 0.4475 | 0.0544 | 50 | 0.6010 |
| 0.4822 | 0.1088 | 100 | 0.6521 |
| 0.2853 | 0.1631 | 150 | 0.3915 |
| 0.2873 | 0.2175 | 200 | 0.3247 |
| 0.2422 | 0.2719 | 250 | 0.2591 |
| 0.3683 | 0.3263 | 300 | 0.2232 |
| 0.2272 | 0.3806 | 350 | 0.1659 |
| 0.1724 | 0.4350 | 400 | 0.1497 |
| 0.1624 | 0.4894 | 450 | 0.1296 |
| 0.1485 | 0.5438 | 500 | 0.1270 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1