README.md

metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: cord-classif-model
    results: []

cord-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: 0.2013
• 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
0.7042	0.1111	1	0.6871	0.5
0.7058	0.2222	2	0.6750	0.6
0.6416	0.3333	3	0.6667	0.9
0.6936	0.4444	4	0.6343	0.7
0.6629	0.5556	5	0.6190	0.9
0.7195	0.6667	6	0.5947	0.9
0.6868	0.7778	7	0.6155	0.9
0.6476	0.8889	8	0.5540	0.9
0.7552	1.0	9	0.5931	0.9
0.5168	1.1111	10	0.5694	0.9
0.4808	1.2222	11	0.5690	0.9
0.6157	1.3333	12	0.5573	0.9
0.5479	1.4444	13	0.5512	0.9
0.4646	1.5556	14	0.5307	0.9
0.4772	1.6667	15	0.5170	0.9
0.4864	1.7778	16	0.5357	0.9
0.4775	1.8889	17	0.4613	0.9
0.6061	2.0	18	0.4886	0.9
0.3524	2.1111	19	0.4830	0.9
0.3927	2.2222	20	0.4916	0.9
0.4264	2.3333	21	0.4799	0.9
0.3172	2.4444	22	0.4445	0.9
0.3645	2.5556	23	0.4737	0.9
0.3675	2.6667	24	0.4502	0.9
0.5295	2.7778	25	0.4212	0.9
0.2749	2.8889	26	0.4278	0.9
0.3156	3.0	27	0.4320	0.9
0.3443	3.1111	28	0.3981	0.9
0.3151	3.2222	29	0.3999	0.9
0.3343	3.3333	30	0.3813	0.9
0.2849	3.4444	31	0.3708	0.9
0.203	3.5556	32	0.3883	0.9
0.2974	3.6667	33	0.3516	0.9
0.39	3.7778	34	0.3712	0.9
0.3439	3.8889	35	0.3459	0.9
0.311	4.0	36	0.3271	0.9
0.2814	4.1111	37	0.3801	0.9
0.161	4.2222	38	0.3165	0.9
0.14	4.3333	39	0.2890	0.9
0.3928	4.4444	40	0.3259	0.9
0.1812	4.5556	41	0.2839	0.9
0.21	4.6667	42	0.2612	1.0
0.1424	4.7778	43	0.3312	1.0
0.2238	4.8889	44	0.2660	0.9
0.2472	5.0	45	0.2653	0.9
0.1143	5.1111	46	0.2353	1.0
0.1888	5.2222	47	0.2542	1.0
0.2183	5.3333	48	0.2679	1.0
0.1019	5.4444	49	0.2618	1.0
0.2266	5.5556	50	0.2353	1.0
0.15	5.6667	51	0.2337	1.0
0.2253	5.7778	52	0.2540	1.0
0.1451	5.8889	53	0.2390	1.0
0.1481	6.0	54	0.2346	0.9
0.1112	6.1111	55	0.2171	1.0
0.1482	6.2222	56	0.2044	1.0
0.181	6.3333	57	0.1914	1.0
0.1091	6.4444	58	0.1911	1.0
0.1205	6.5556	59	0.1990	1.0
0.16	6.6667	60	0.1984	1.0
0.0967	6.7778	61	0.1852	1.0
0.1812	6.8889	62	0.1976	1.0
0.1711	7.0	63	0.1766	1.0
0.1959	7.1111	64	0.2000	1.0
0.4228	7.2222	65	0.2017	1.0
0.506	7.3333	66	0.1828	1.0
0.1869	7.4444	67	0.1728	1.0
0.0914	7.5556	68	0.1846	1.0
0.1622	7.6667	69	0.2005	1.0
0.0884	7.7778	70	0.2367	1.0
0.1018	7.8889	71	0.1785	1.0
0.1132	8.0	72	0.2013	1.0

Framework versions

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