qwen25_7b_rm_acc_5e6_2ep
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: 1.5700
- Accuracy: 0.67
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 16
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.616 | 0.2424 | 10 | 0.6253 | 0.69 |
| 0.0111 | 0.4848 | 20 | 1.6194 | 0.6267 |
| 0.0199 | 0.7273 | 30 | 1.3252 | 0.6667 |
| 0.0151 | 0.9697 | 40 | 2.5704 | 0.6467 |
| 0.0084 | 1.1939 | 50 | 2.2932 | 0.6633 |
| 0.0235 | 1.4364 | 60 | 2.2684 | 0.6333 |
| 0.0264 | 1.6788 | 70 | 1.5395 | 0.6767 |
| 0.0322 | 1.9212 | 80 | 1.2030 | 0.6767 |
| 0.0018 | 2.1455 | 90 | 1.2336 | 0.69 |
| 0.0001 | 2.3879 | 100 | 1.4934 | 0.6667 |
| 0.0004 | 2.6303 | 110 | 1.5528 | 0.67 |
| 0.0 | 2.8727 | 120 | 1.5700 | 0.67 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1
- Downloads last month
- 1