MAE

This model is a fine-tuned version of facebook/vit-mae-base on the Circularmachines/batch_indexing_machine_224x224_images dataset. It achieves the following results on the evaluation set:

• Loss: 0.2263

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: 4.6875e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.249	1.0	7705	0.2445
0.2269	2.0	15410	0.2373
0.2401	3.0	23115	0.2334
0.2202	4.0	30820	0.2305
0.2173	5.0	38525	0.2283
0.2347	6.0	46230	0.2282
0.2304	7.0	53935	0.2268
0.2267	8.0	61640	0.2262
0.2177	9.0	69345	0.2254
0.2175	10.0	77050	0.2262

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3