fine_tuned_all_domains_balanced_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: 0.1147
• Accuracy: 0.9703

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: 32
• eval_batch_size: 32
• 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
0.1945	0.0860	500	0.4187	0.8732
0.171	0.1720	1000	0.1541	0.9371
0.1235	0.2580	1500	0.1469	0.9451
0.1233	0.3441	2000	0.1433	0.9532
0.1109	0.4301	2500	0.1395	0.9541
0.108	0.5161	3000	0.1134	0.9622
0.0864	0.6021	3500	0.1452	0.9649
0.0743	0.6881	4000	0.1336	0.9676
0.0637	0.7741	4500	0.1147	0.9703

Framework versions

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