v11
This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the freede_router dataset. It achieves the following results on the evaluation set:
- Loss: 0.2651
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: 1.5e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7767 | 0.7782 | 50 | 0.7420 |
0.4193 | 1.5564 | 100 | 0.4160 |
0.2815 | 2.3346 | 150 | 0.3077 |
0.2131 | 3.1128 | 200 | 0.2698 |
0.2117 | 3.8911 | 250 | 0.2534 |
0.1512 | 4.6693 | 300 | 0.2489 |
0.1235 | 5.4475 | 350 | 0.2626 |
0.126 | 6.2451 | 400 | 0.2628 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 0