MATH_training_response_gpt-4o-mini_only_right
This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the MATH_training_response_gpt-4o-mini_only_right dataset. It achieves the following results on the evaluation set:
- Loss: 0.0833
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: 0.0001
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1197 | 0.1455 | 200 | 0.1125 |
| 0.0971 | 0.2909 | 400 | 0.1020 |
| 0.0967 | 0.4364 | 600 | 0.0961 |
| 0.0991 | 0.5818 | 800 | 0.0912 |
| 0.0801 | 0.7273 | 1000 | 0.0895 |
| 0.1174 | 0.8727 | 1200 | 0.0874 |
| 0.067 | 1.0182 | 1400 | 0.0862 |
| 0.09 | 1.1636 | 1600 | 0.0863 |
| 0.0777 | 1.3091 | 1800 | 0.0850 |
| 0.051 | 1.4545 | 2000 | 0.0841 |
| 0.074 | 1.6 | 2200 | 0.0845 |
| 0.0667 | 1.7455 | 2400 | 0.0839 |
| 0.0456 | 1.8909 | 2600 | 0.0835 |
Framework versions
- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 4