decompiler-distil-v4 – AI Model by raafatabualazm | AlphaNeural AI

You can deploy this model and start earning money today!

raafatabualazm/
decompiler-distil-v4

like

0

text-generation

Qwen/Qwen3-4B-Thinking-2507

Views

No views yet

decompiler-distil-v4

This model is a fine-tuned version of Qwen/Qwen3-4B-Thinking-2507 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5321

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
2.8394	0.2255	100	0.5880
2.959	0.4510	200	0.5572
2.595	0.6764	300	0.5390
2.3139	0.9019	400	0.5321

Framework versions

PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 4.3.0
Tokenizers 0.22.1