sft
This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the eedi dataset. It achieves the following results on the evaluation set:
- Loss: 0.8951
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2332 | 0.1626 | 20 | 1.2680 |
| 1.0315 | 0.3252 | 40 | 0.9880 |
| 0.8677 | 0.4878 | 60 | 0.9157 |
| 0.8893 | 0.6504 | 80 | 0.8641 |
| 0.8072 | 0.8130 | 100 | 0.8326 |
| 0.7722 | 0.9756 | 120 | 0.7950 |
| 0.5838 | 1.1382 | 140 | 0.8270 |
| 0.6009 | 1.3008 | 160 | 0.7669 |
| 0.5373 | 1.4634 | 180 | 0.7591 |
| 0.5617 | 1.6260 | 200 | 0.7382 |
| 0.5768 | 1.7886 | 220 | 0.7313 |
| 0.5072 | 1.9512 | 240 | 0.7281 |
| 0.3148 | 2.1138 | 260 | 0.7919 |
| 0.2612 | 2.2764 | 280 | 0.9314 |
| 0.2222 | 2.4390 | 300 | 0.9256 |
| 0.2427 | 2.6016 | 320 | 0.8956 |
| 0.2289 | 2.7642 | 340 | 0.8932 |
| 0.1885 | 2.9268 | 360 | 0.8958 |
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
- 0