JaesonGu/flare-plug-vit

plug-classif-model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5418
• Accuracy: 1.0

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.695	0.1538	1	0.7619	0.1429
0.6096	0.3077	2	0.7630	0.2857
0.7567	0.4615	3	0.7897	0.2857
0.6185	0.6154	4	0.7943	0.2857
0.5869	0.7692	5	0.7740	0.2857
0.8098	0.9231	6	0.7680	0.4286
0.402	1.0	7	0.7535	0.2857
0.5498	1.1538	8	0.7027	0.2857
0.5556	1.3077	9	0.7100	0.2857
0.4257	1.4615	10	0.6922	0.4286
0.5488	1.6154	11	0.6592	0.4286
0.4829	1.7692	12	0.7471	0.2857
0.677	1.9231	13	0.6789	0.4286
0.3105	2.0	14	0.6908	0.4286
0.461	2.1538	15	0.6732	0.4286
0.388	2.3077	16	0.6960	0.5714
0.4678	2.4615	17	0.6274	0.5714
0.4753	2.6154	18	0.6437	0.5714
0.5482	2.7692	19	0.6570	0.5714
0.4301	2.9231	20	0.6745	0.7143
0.177	3.0	21	0.6477	0.4286
0.4159	3.1538	22	0.6018	0.5714
0.3089	3.3077	23	0.5951	0.5714
0.4568	3.4615	24	0.5659	0.8571
0.4791	3.6154	25	0.5845	0.8571
0.4097	3.7692	26	0.6343	0.8571
0.4327	3.9231	27	0.5930	0.8571
0.1493	4.0	28	0.5458	1.0
0.3021	4.1538	29	0.5421	1.0
0.3166	4.3077	30	0.5646	1.0
0.2537	4.4615	31	0.5960	0.8571
0.2853	4.6154	32	0.5636	0.8571
0.3353	4.7692	33	0.5513	1.0
0.3462	4.9231	34	0.5735	0.8571
0.1871	5.0	35	0.5109	1.0
0.2953	5.1538	36	0.5797	1.0
0.2655	5.3077	37	0.5374	1.0
0.352	5.4615	38	0.5245	1.0
0.3536	5.6154	39	0.5387	0.8571
0.2579	5.7692	40	0.5067	1.0
0.3356	5.9231	41	0.5992	0.8571
0.1094	6.0	42	0.5778	0.8571
0.3345	6.1538	43	0.4571	1.0
0.2314	6.3077	44	0.4651	1.0
0.3312	6.4615	45	0.4798	1.0
0.206	6.6154	46	0.4911	1.0
0.3101	6.7692	47	0.4788	1.0
0.3	6.9231	48	0.5418	1.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cpu
• Datasets 3.2.0
• Tokenizers 0.21.0