ASD_Behavour-trainining2

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9525
• Accuracy: 0.3636

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0667	2	1.0015	0.5556
No log	1.0667	4	0.9530	0.5556
No log	2.0667	6	1.2045	0.2222
No log	3.0667	8	1.5476	0.2593
0.4992	4.0667	10	1.3886	0.2222
0.4992	5.0667	12	1.1887	0.3333
0.4992	6.0667	14	1.0209	0.5185
0.4992	7.0667	16	0.9728	0.7407
0.4992	8.0667	18	0.9164	0.6667
0.3577	9.0667	20	0.8789	0.6667
0.3577	10.0667	22	0.8177	0.6667
0.3577	11.0667	24	0.8500	0.6296
0.3577	12.0667	26	0.9112	0.6296
0.3577	13.0667	28	0.9497	0.6667
0.1819	14.0667	30	0.9656	0.6667

Framework versions

• Transformers 4.41.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1