final-algae-swin-wirs

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

• Loss: 0.7645
• Accuracy: 0.6725

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3024	1.0	120	0.7645	0.6725
1.2375	2.0	240	0.8013	0.6673
1.1875	3.0	360	0.8251	0.6649
1.187	4.0	480	0.8960	0.6403
1.1472	5.0	600	0.9558	0.6244
1.1374	6.0	720	1.1951	0.4877
1.1114	7.0	840	1.1109	0.5358
1.1201	8.0	960	0.9724	0.6227
1.0801	9.0	1080	0.9913	0.5863
1.0995	10.0	1200	1.0117	0.5933
1.0817	11.0	1320	1.0239	0.5951
1.0679	12.0	1440	1.0381	0.5839
1.094	13.0	1560	1.0480	0.5910
1.0325	14.0	1680	1.0671	0.5839
1.0087	15.0	1800	1.0133	0.5892
1.0525	16.0	1920	1.0332	0.5775
1.0614	17.0	2040	1.0085	0.5939
1.0065	18.0	2160	1.0070	0.5974
1.0474	19.0	2280	1.0023	0.5898
1.0346	20.0	2400	1.0072	0.5839
1.0226	21.0	2520	1.0219	0.5792
1.0474	22.0	2640	1.0106	0.5880
0.983	23.0	2760	1.0020	0.5874
0.9997	24.0	2880	1.0838	0.5593
1.0074	25.0	3000	1.0781	0.5593
1.0	26.0	3120	1.0378	0.5751
1.0279	27.0	3240	1.0737	0.5604
0.9696	28.0	3360	1.1385	0.5123
0.9862	29.0	3480	1.1236	0.5282
1.0155	30.0	3600	1.0415	0.5798
0.9723	31.0	3720	1.1447	0.5258
0.9935	32.0	3840	1.1166	0.5323
0.9965	33.0	3960	1.0502	0.5716
0.9645	34.0	4080	1.1316	0.5329
0.9771	35.0	4200	1.1860	0.5170
0.9976	36.0	4320	1.2937	0.4906
0.9207	37.0	4440	1.2272	0.5135
0.9813	38.0	4560	1.2067	0.5258
0.9337	39.0	4680	1.2162	0.5282
0.9628	40.0	4800	1.2700	0.5059
0.9561	41.0	4920	1.2428	0.5094
0.9208	42.0	5040	1.2271	0.5158
0.9097	43.0	5160	1.2388	0.5182
0.9487	44.0	5280	1.1966	0.5264
0.9386	45.0	5400	1.2107	0.5258
0.9291	46.0	5520	1.2893	0.4977
0.9357	47.0	5640	1.2764	0.5041
0.9064	48.0	5760	1.2710	0.5012
0.9032	49.0	5880	1.2695	0.5
0.9423	50.0	6000	1.2703	0.4982

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu117
• Datasets 2.9.0
• Tokenizers 0.13.2