test_model

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2975
• Accuracy: 0.9453

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	46	0.3305	0.9196
No log	2.0	92	0.2336	0.9164
No log	3.0	138	0.1981	0.9421
No log	4.0	184	0.1994	0.9421
No log	5.0	230	0.2091	0.9421
No log	6.0	276	0.2382	0.9453
No log	7.0	322	0.2608	0.9453
No log	8.0	368	0.2621	0.9453
No log	9.0	414	0.2757	0.9486
No log	10.0	460	0.2999	0.9486
0.1173	11.0	506	0.2928	0.9486
0.1173	12.0	552	0.2863	0.9421
0.1173	13.0	598	0.2875	0.9453
0.1173	14.0	644	0.2922	0.9453
0.1173	15.0	690	0.2966	0.9453
0.1173	16.0	736	0.2975	0.9453

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3