Modelpublic

Moustafa3092/saudi-eou-qwen-adapter-livkit

sourceHugging Faceotherupdated 10mo agoView on Hugging Face

0likes8downloads

Model Card

saudieouqwen

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
—trainbatchsize: 16
—evalbatchsize: 32
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_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