metadata
library_name: transformers
license: cc-by-4.0
base_model: Qwen3-4B-Concise-SimPO-StrategyB-Stage1
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: Qwen3-4B-Concise-SimPO-StrategyB-Stage2
results: []
Qwen3-4B-Concise-SimPO-StrategyB-Stage1
This model is a fine-tuned version of davidanugraha/Qwen3-4B-Concise-SimPO-StrategyB-Stage1, in which the base model is Qwen/Qwen3-4B.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- total_eval_batch_size: 32
- 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0