Teacher_forget_RL_data_QwQ-Preview
This model is a fine-tuned version of Qwen/Qwen2.5-Math-7B on the Teacher_forget_RL_data_QwQ-Preview dataset. It achieves the following results on the evaluation set:
- Loss: 0.3434
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.373 | 0.1650 | 100 | 0.3495 |
0.2525 | 0.3300 | 200 | 0.3356 |
0.307 | 0.4950 | 300 | 0.3277 |
0.389 | 0.6601 | 400 | 0.3228 |
0.2299 | 0.8251 | 500 | 0.3177 |
0.2811 | 0.9901 | 600 | 0.3139 |
0.0677 | 1.1551 | 700 | 0.3337 |
0.1073 | 1.3201 | 800 | 0.3280 |
0.1223 | 1.4851 | 900 | 0.3278 |
0.1587 | 1.6502 | 1000 | 0.3272 |
0.1383 | 1.8152 | 1100 | 0.3256 |
0.1098 | 1.9802 | 1200 | 0.3245 |
0.0971 | 2.1452 | 1300 | 0.3430 |
0.0713 | 2.3102 | 1400 | 0.3417 |
0.0695 | 2.4752 | 1500 | 0.3426 |
0.0866 | 2.6403 | 1600 | 0.3442 |
0.0703 | 2.8053 | 1700 | 0.3434 |
0.0356 | 2.9703 | 1800 | 0.3435 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support