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: 0.5306

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: 43

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	2	5.7835
No log	2.0	4	5.5864
No log	3.0	6	5.3756
No log	4.0	8	5.1400
No log	5.0	10	4.8788
No log	6.0	12	4.6019
No log	7.0	14	4.3225
No log	8.0	16	4.0563
No log	9.0	18	3.8043
No log	10.0	20	3.5541
No log	11.0	22	3.3095
No log	12.0	24	3.0757
No log	13.0	26	2.8604
No log	14.0	28	2.6582
No log	15.0	30	2.4608
No log	16.0	32	2.2602
No log	17.0	34	2.0589
No log	18.0	36	1.8666
No log	19.0	38	1.6800
No log	20.0	40	1.5017
No log	21.0	42	1.3370
No log	22.0	44	1.1987
No log	23.0	46	1.0752
No log	24.0	48	0.9697
No log	25.0	50	0.8877
No log	26.0	52	0.8270
No log	27.0	54	0.7765
No log	28.0	56	0.7293
No log	29.0	58	0.6861
No log	30.0	60	0.6527
No log	31.0	62	0.6246
No log	32.0	64	0.6006
No log	33.0	66	0.5805
No log	34.0	68	0.5658
No log	35.0	70	0.5547
No log	36.0	72	0.5487
No log	37.0	74	0.5440
No log	38.0	76	0.5409
No log	39.0	78	0.5386
No log	40.0	80	0.5354
No log	41.0	82	0.5327
No log	42.0	84	0.5313
No log	43.0	86	0.5306

Framework versions

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