metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2-7B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 502009a6-38f2-4c2e-8637-7031a8638511
results: []
502009a6-38f2-4c2e-8637-7031a8638511
This model is a fine-tuned version of unsloth/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0718
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: 0.000217
- 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 | 0.0007 | 1 | 1.3709 |
| 2.273 | 0.0349 | 50 | 1.2857 |
| 2.3177 | 0.0698 | 100 | 1.2862 |
| 2.1619 | 0.1047 | 150 | 1.2346 |
| 1.9841 | 0.1397 | 200 | 1.2007 |
| 2.2834 | 0.1746 | 250 | 1.1518 |
| 1.9584 | 0.2095 | 300 | 1.1206 |
| 2.2907 | 0.2444 | 350 | 1.0983 |
| 2.3411 | 0.2793 | 400 | 1.0796 |
| 2.3673 | 0.3142 | 450 | 1.0725 |
| 2.1397 | 0.3492 | 500 | 1.0718 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1