fine_tuned_per_domain_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: 0.0842
• Accuracy: 0.9714

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
0.1807	0.0915	500	0.3355	0.8881
0.1387	0.1831	1000	0.1860	0.9293
0.1443	0.2746	1500	0.1421	0.9418
0.1143	0.3662	2000	0.1273	0.9517
0.1103	0.4577	2500	0.1393	0.9490
0.1049	0.5492	3000	0.1159	0.9606
0.0809	0.6408	3500	0.1267	0.9526
0.0896	0.7323	4000	0.1104	0.9606
0.0758	0.8239	4500	0.1341	0.9633
0.0811	0.9154	5000	0.0842	0.9714

Framework versions

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