fine_tuned_all_domains_1.5

This model is a fine-tuned version of Qwen/Qwen1.5-1.8B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2531
• Accuracy: 0.9460

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH 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	Accuracy
0.4234	0.0126	500	0.3614	0.8957
0.2949	0.0252	1000	0.2974	0.9101
0.3592	0.0377	1500	0.2913	0.9137
0.3101	0.0503	2000	0.2877	0.9326
0.2923	0.0629	2500	0.2246	0.9290
0.2778	0.0755	3000	0.2472	0.9397
0.2556	0.0881	3500	0.2163	0.9487
0.2986	0.1006	4000	0.2156	0.9478
0.272	0.1132	4500	0.2387	0.9388
0.2363	0.1258	5000	0.4263	0.9326
0.221	0.1384	5500	0.2054	0.9505
0.2478	0.1510	6000	0.2851	0.9451
0.2451	0.1635	6500	0.2730	0.9442
0.1915	0.1761	7000	0.2531	0.9460

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0