metadata
library_name: peft
license: apache-2.0
base_model: unsloth/Qwen2.5-Math-1.5B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 35dc2da3-0828-49ed-afc3-96aa5b734f83
results: []
35dc2da3-0828-49ed-afc3-96aa5b734f83
This model is a fine-tuned version of unsloth/Qwen2.5-Math-1.5B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3746
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: 0.000206
- 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 | 0.0004 | 1 | 0.4857 |
| 0.3779 | 0.0188 | 50 | 0.4184 |
| 0.3734 | 0.0376 | 100 | 0.4047 |
| 0.372 | 0.0564 | 150 | 0.3992 |
| 0.421 | 0.0752 | 200 | 0.3926 |
| 0.3759 | 0.0939 | 250 | 0.3851 |
| 0.3702 | 0.1127 | 300 | 0.3823 |
| 0.329 | 0.1315 | 350 | 0.3779 |
| 0.3325 | 0.1503 | 400 | 0.3753 |
| 0.3586 | 0.1691 | 450 | 0.3744 |
| 0.3685 | 0.1879 | 500 | 0.3746 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1