Modelpublic

Pranavacchu/linuxqa-llora-qwen-1.8b

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes20downloads

Model Card

linuxqa-llora-qwen-1.8b

This model is a fine-tuned version of Qwen/Qwen-1_8B-Chat on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.0897

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
—trainbatchsize: 2
—evalbatchsize: 2
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.1026	0.1111	200	0.0986
0.0929	0.2222	400	0.1216
0.0971	0.3333	600	0.0982
0.0949	0.4444	800	0.1022
0.0936	0.5556	1000	0.0931
0.0967	0.6667	1200	0.0909
0.0931	0.7778	1400	0.0973
0.0928	0.8889	1600	0.0937
0.0924	1.0	1800	0.0931
0.0962	1.1111	2000	0.0917
0.0945	1.2222	2200	0.0901
0.0929	1.3333	2400	0.0914
0.0913	1.4444	2600	0.0905
0.0913	1.5556	2800	0.0902
0.0914	1.6667	3000	0.0918
0.0906	1.7778	3200	0.0922
0.0893	1.8889	3400	0.0899
0.0902	2.0	3600	0.0897

Framework versions

—PEFT 0.15.2
—Transformers 4.51.3
—Pytorch 2.6.0+cu124
—Datasets 2.14.4
—Tokenizers 0.21.1