qwen25_7b_rm_acc_5e5_5ep
This model is a fine-tuned version of Jennny/qwen25_7b_sft_math on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0929
- Accuracy: 0.6967
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 32
- optimizer: Use OptimizerNames.PAGED_ADAMW 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: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7873 | 0.4848 | 10 | 0.6914 | 0.5333 |
| 0.5594 | 0.9697 | 20 | 0.5069 | 0.7667 |
| 0.3625 | 1.4848 | 30 | 0.5938 | 0.6767 |
| 0.3695 | 1.9697 | 40 | 0.6109 | 0.73 |
| 0.1204 | 2.4848 | 50 | 3.3507 | 0.7433 |
| 0.0809 | 2.9697 | 60 | 1.2752 | 0.71 |
| 0.0114 | 3.4848 | 70 | 1.9357 | 0.72 |
| 0.0248 | 3.9697 | 80 | 2.2252 | 0.7067 |
| 0.0003 | 4.4848 | 90 | 2.0998 | 0.6967 |
| 0.002 | 4.9697 | 100 | 2.0929 | 0.6967 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1
- Downloads last month
- 1