Action_agent_small_34_class

This model is a fine-tuned version of microsoft/resnet-18 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.0952

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: 1e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0	0.32	100	nan	0.0952
0.0	0.64	200	nan	0.0952
0.0	0.96	300	nan	0.0952
0.0	1.27	400	nan	0.0952
0.0	1.59	500	nan	0.0952
0.0	1.91	600	nan	0.0952
0.0	2.23	700	nan	0.0952
0.0	2.55	800	nan	0.0952
0.0	2.87	900	nan	0.0952
0.0	3.18	1000	nan	0.0952
0.0	3.5	1100	nan	0.0952
0.0	3.82	1200	nan	0.0952
0.0	4.14	1300	nan	0.0952
0.0	4.46	1400	nan	0.0952
0.0	4.78	1500	nan	0.0952
0.0	5.1	1600	nan	0.0952
0.0	5.41	1700	nan	0.0952
0.0	5.73	1800	nan	0.0952
0.0	6.05	1900	nan	0.0952
0.0	6.37	2000	nan	0.0952
0.0	6.69	2100	nan	0.0952
0.0	7.01	2200	nan	0.0952
0.0	7.32	2300	nan	0.0952
0.0	7.64	2400	nan	0.0952
0.0	7.96	2500	nan	0.0952
0.0	8.28	2600	nan	0.0952
0.0	8.6	2700	nan	0.0952
0.0	8.92	2800	nan	0.0952
0.0	9.24	2900	nan	0.0952
0.0	9.55	3000	nan	0.0952
0.0	9.87	3100	nan	0.0952

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2