metadata
library_name: transformers
license: other
base_model: /HOME/paratera_xy/pxy1182/HDD_POOL/model/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: sft_safe_projection_merge400d_step30
results: []
sft_safe_projection_merge400d_step30
This model is a fine-tuned version of /HOME/paratera_xy/pxy1182/HDD_POOL/model/Qwen2.5-7B-Instruct on the saferlhf2_sft 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: 1e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.57.3
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.1