ahmedheakl/gg-armv8-O0

Check out more datails here:

• Paper: https://arxiv.org/abs/2506.14606
• Code: https://github.com/ahmedheakl/Guaranteed-Guess

ex19_qwen2.5-1.5b-1M-stack-16kcw

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on the stack_16k, the anghabench_16k_1 and the anghabench_16k_2 datasets. It achieves the following results on the evaluation set:

• Loss: 0.0003

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: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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
0.0037	0.1645	25000	0.0028
0.003	0.3289	50000	0.0017
0.002	0.4934	75000	0.0012
0.0002	0.6579	100000	0.0011
0.0011	0.8224	125000	0.0009
0.001	0.9868	150000	0.0007
0.0013	1.1513	175000	0.0005
0.0004	1.3158	200000	0.0005
0.0007	1.4802	225000	0.0004
0.0007	1.6447	250000	0.0004
0.0003	1.8092	275000	0.0003
0.0002	1.9736	300000	0.0003

Framework versions

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