metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: dc24576a-0c53-4d2e-911c-b0d3ac3c1d60
results: []
dc24576a-0c53-4d2e-911c-b0d3ac3c1d60
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1754
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: 100
- 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 | 0.0000 | 1 | 1.6356 |
| 0.6246 | 0.0019 | 50 | 0.3264 |
| 0.4428 | 0.0039 | 100 | 0.3348 |
| 0.2977 | 0.0058 | 150 | 0.2764 |
| 0.3748 | 0.0077 | 200 | 0.2430 |
| 0.2707 | 0.0096 | 250 | 0.2317 |
| 0.2267 | 0.0116 | 300 | 0.2215 |
| 0.1907 | 0.0135 | 350 | 0.1911 |
| 0.3465 | 0.0154 | 400 | 0.1820 |
| 0.3195 | 0.0173 | 450 | 0.1766 |
| 0.2919 | 0.0193 | 500 | 0.1754 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1