ADHD_Test_qa_model

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

• Loss: 1.0061

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	5.7461
No log	2.0	4	5.5441
No log	3.0	6	5.3226
No log	4.0	8	5.0725
No log	5.0	10	4.8020
No log	6.0	12	4.5135
No log	7.0	14	4.2225
No log	8.0	16	3.9429
No log	9.0	18	3.6847
No log	10.0	20	3.4510
No log	11.0	22	3.2467
No log	12.0	24	3.0685
No log	13.0	26	2.9113
No log	14.0	28	2.7682
No log	15.0	30	2.6341
No log	16.0	32	2.4968
No log	17.0	34	2.3575
No log	18.0	36	2.2179
No log	19.0	38	2.0802
No log	20.0	40	1.9476
No log	21.0	42	1.8254
No log	22.0	44	1.6981
No log	23.0	46	1.5769
No log	24.0	48	1.4611
No log	25.0	50	1.3675
No log	26.0	52	1.2925
No log	27.0	54	1.2285
No log	28.0	56	1.1718
No log	29.0	58	1.1221
No log	30.0	60	1.0865
No log	31.0	62	1.0644
No log	32.0	64	1.0428
No log	33.0	66	1.0304
No log	34.0	68	1.0209
No log	35.0	70	1.0109
No log	36.0	72	1.0079
No log	37.0	74	1.0096
No log	38.0	76	1.0071
No log	39.0	78	1.0064
No log	40.0	80	1.0061

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2