ahmedheakl/ex13_qwen2.5_0.5b_1M_stack_armv5_O0

qwen2.5_0.5b_1M_stack_16kcw_2ep

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct on the anghabench_1M_1, the anghabench_1M_2 and the stack datasets. It achieves the following results on the evaluation set:

• Loss: 0.0020

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-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 4
• 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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0064	0.3912	61000	0.0041
0.0029	0.7825	122000	0.0032
0.0023	1.1737	183000	0.0024
0.0018	1.5649	244000	0.0021
0.0011	1.9562	305000	0.0020

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3