fine_tuned_wp_callback10

This model is a fine-tuned version of Qwen/Qwen2-1.5B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0638
• Accuracy: 0.9897

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: 2e-05
• 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6619	0.0285	100	0.9984	0.8816
0.4074	0.0570	200	0.2584	0.9194
0.2873	0.0856	300	0.5169	0.9393
0.1938	0.1141	400	0.1101	0.9843
0.123	0.1426	500	0.0877	0.9830
0.2114	0.1711	600	0.2161	0.9599
0.1381	0.1997	700	0.1234	0.9782
0.1311	0.2282	800	0.4941	0.9496
0.1807	0.2567	900	0.1084	0.9730
0.143	0.2852	1000	0.1180	0.9801
0.0847	0.3137	1100	0.0704	0.9849
0.0757	0.3423	1200	0.0436	0.9884
0.1022	0.3708	1300	0.0757	0.9811
0.1659	0.3993	1400	0.1003	0.9823
0.1926	0.4278	1500	0.0462	0.9901
0.1627	0.4564	1600	0.0925	0.9817
0.1789	0.4849	1700	0.2666	0.9599
0.1518	0.5134	1800	0.0978	0.9775
0.0888	0.5419	1900	0.0871	0.9791
0.1079	0.5705	2000	0.0390	0.9920
0.04	0.5990	2100	0.0571	0.9907
0.0573	0.6275	2200	0.0521	0.9878
0.0633	0.6560	2300	0.0497	0.9891
0.0857	0.6845	2400	0.0575	0.9894
0.1061	0.7131	2500	0.0628	0.9894
0.0575	0.7416	2600	0.0721	0.9891
0.0741	0.7701	2700	0.1140	0.9772
0.0662	0.7986	2800	0.1028	0.9804
0.0585	0.8272	2900	0.0419	0.9926
0.0647	0.8557	3000	0.0638	0.9897

Framework versions

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