saudi_eou_qwen

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the saudi_eou dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1497

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: 5e-06
  • train_batch_size: 16
  • eval_batch_size: 32
  • seed: 42
  • 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: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss
0.1887 0.2632 100 0.1556
0.1915 0.5263 200 0.1515
0.1352 0.7895 300 0.1373
0.1611 1.0526 400 0.1280
0.117 1.3158 500 0.1194
0.1145 1.5789 600 0.1213
0.121 1.8421 700 0.1117
0.0586 2.1053 800 0.1188
0.0495 2.3684 900 0.1218
0.0818 2.6316 1000 0.1147
0.0688 2.8947 1100 0.1358
0.0151 3.1579 1200 0.1242
0.0296 3.4211 1300 0.1345
0.0243 3.6842 1400 0.1320
0.0407 3.9474 1500 0.1485
0.0129 4.2105 1600 0.1466
0.0138 4.4737 1700 0.1453
0.0272 4.7368 1800 0.1512
0.0202 5.0 1900 0.1497

Framework versions

  • PEFT 0.17.1
  • Transformers 4.57.3
  • Pytorch 2.9.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.1
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Moustafa3092/saudi-eou-qwen-adapter-livkit

Base model

Qwen/Qwen2-0.5B
Adapter
(502)
this model