| --- |
| library_name: peft |
| license: mit |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
| tags: |
| - alignment-handbook |
| - trl |
| - sft |
| - generated_from_trainer |
| datasets: |
| - tttx/replicate-problem-10-ttt-step1-master |
| model-index: |
| - name: replicate-problem-10-ttt-step1 |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # replicate-problem-10-ttt-step1 |
|
|
| This model is a fine-tuned version of [tttx/sft-32b-020925-19k-5ep](https://huggingface.co/tttx/sft-32b-020925-19k-5ep) on the tttx/replicate-problem-10-ttt-step1-master dataset. |
|
|
| ## 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: 2 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - distributed_type: multi-GPU |
| - num_devices: 8 |
| - total_train_batch_size: 16 |
| - 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: 2 |
| |
| ### Training results |
| |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.13.2 |
| - Transformers 4.47.0.dev0 |
| - Pytorch 2.4.0+cu121 |
| - Datasets 3.1.0 |
| - Tokenizers 0.20.3 |
