Deepseek-1.5B_pre1_sft_short_cot_lr2e-5_prompt_direct
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2596 | 1.3459 | 500 | 0.2824 |
| 0.261 | 2.6918 | 1000 | 0.2804 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.5.1+cu124
- Datasets 2.21.0
- Tokenizers 0.20.3