ex22

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct on the x86_opt_0, the x86_opt_1 and the x86_opt_2 datasets. It achieves the following results on the evaluation set:

• Loss: 0.0065

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: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• total_eval_batch_size: 2
• 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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0142	0.9361	61000	0.0092
0.005	1.8722	122000	0.0065

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0