large-algae-vit-wirs

This model is a fine-tuned version of samitizerxu/large-algae-vit-wirs on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9128
• Accuracy: 0.6209

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1662	1.0	120	0.9128	0.6209
1.0885	2.0	240	0.9469	0.6138
1.1315	3.0	360	1.0919	0.5757
1.0542	4.0	480	1.2291	0.5599
1.028	5.0	600	1.1931	0.5599
1.0023	6.0	720	1.1548	0.5675
1.0176	7.0	840	1.0932	0.5757
0.992	8.0	960	1.1387	0.5751
0.9891	9.0	1080	1.2387	0.5464
0.9635	10.0	1200	1.3772	0.5428
0.9764	11.0	1320	1.4329	0.5258
0.9375	12.0	1440	1.2830	0.5522
0.9574	13.0	1560	1.4003	0.5229
0.9907	14.0	1680	1.3447	0.5423
0.9507	15.0	1800	1.2907	0.5604
0.9866	16.0	1920	1.4578	0.5393
0.9297	17.0	2040	1.4779	0.5282
0.9385	18.0	2160	1.3874	0.5469
0.9951	19.0	2280	1.2976	0.5587
0.9794	20.0	2400	1.3110	0.5569
0.9974	21.0	2520	1.3649	0.5276
0.9284	22.0	2640	1.3713	0.5364
0.9144	23.0	2760	1.4117	0.5340
0.9771	24.0	2880	1.3836	0.5358
0.8994	25.0	3000	1.5077	0.5282
0.9061	26.0	3120	1.4622	0.5329
0.9071	27.0	3240	1.4303	0.5393
0.9288	28.0	3360	1.4556	0.5329
0.9285	29.0	3480	1.3900	0.5446
0.8955	30.0	3600	1.4082	0.5387

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2