fine_tuned_eli5_balanced

This model is a fine-tuned version of Qwen/Qwen2-1.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0877
• Accuracy: 0.9782

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4283	0.1064	100	0.2736	0.9031
0.2571	0.2128	200	0.2150	0.9225
0.1891	0.3191	300	0.1402	0.9408
0.1541	0.4255	400	0.1498	0.9476
0.1554	0.5319	500	0.1427	0.9434
0.1291	0.6383	600	0.0966	0.9653
0.1038	0.7447	700	0.0928	0.9656
0.1007	0.8511	800	0.0870	0.9707
0.1037	0.9574	900	0.0838	0.9725
0.0563	1.0638	1000	0.1094	0.9749
0.0319	1.1702	1100	0.1193	0.9746
0.0541	1.2766	1200	0.0877	0.9782

Framework versions

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