metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: ab37478f-15bb-4d01-970f-78a9c6215753
results: []
ab37478f-15bb-4d01-970f-78a9c6215753
This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.7255
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: 0.000205
- train_batch_size: 4
- eval_batch_size: 4
- seed: 50
- 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 | 4.5647 |
| 3.2376 | 0.0023 | 50 | 3.3136 |
| 3.173 | 0.0045 | 100 | 3.0686 |
| 3.3612 | 0.0068 | 150 | 2.9804 |
| 3.3344 | 0.0090 | 200 | 2.9288 |
| 2.9887 | 0.0113 | 250 | 2.8600 |
| 3.2181 | 0.0135 | 300 | 2.8021 |
| 3.2327 | 0.0158 | 350 | 2.7587 |
| 3.1479 | 0.0181 | 400 | 2.7355 |
| 3.1241 | 0.0203 | 450 | 2.7267 |
| 2.8884 | 0.0226 | 500 | 2.7255 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1