qwen-skripsi-v1

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1767

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5668	0.3968	50	0.5044
0.4804	0.7937	100	0.3970
0.302	1.1905	150	0.2971
0.2426	1.5873	200	0.2380
0.1924	1.9841	250	0.1977
0.2158	2.3810	300	0.1855
0.1642	2.7778	350	0.1767

Framework versions

• PEFT 0.18.0
• Transformers 4.57.1
• Pytorch 2.9.1+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1