DifferentiableEvolutionaryRL/DERL-Meta-Optimizer-Init-Qwen2.5-0.5B-Instruct

sft

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the sft_with_format dataset.

Model description

The model is the base Meta-Optimizer for DERL used for all tasks.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 128
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 4096
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 12.0

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.1