vit-large-artifacts

This model is a fine-tuned version of kakaobrain/vit-large-patch16-512 on the KyriaAnnwyn/artifacts_ds dataset. It achieves the following results on the evaluation set:

• Loss: 0.5995
• Accuracy: 0.6705

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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7001	0.01	100	0.6414	0.6559
0.6288	0.01	200	0.6666	0.6559
0.7237	0.02	300	0.7087	0.6559
0.8741	0.03	400	0.6739	0.6257
0.6093	0.04	500	0.6462	0.6559
0.5801	0.04	600	0.6822	0.6559
0.594	0.05	700	1.9948	0.6395
0.7724	0.06	800	0.6566	0.6553
0.6976	0.07	900	0.6774	0.6325
0.6583	0.07	1000	0.7175	0.3517
0.6779	0.08	1100	0.7012	0.6559
0.6478	0.09	1200	0.6336	0.6559
0.7405	0.1	1300	0.6577	0.6559
0.7362	0.1	1400	0.6630	0.6142
0.535	0.11	1500	0.7445	0.6559
0.7338	0.12	1600	0.7046	0.4718
0.6519	0.13	1700	0.6601	0.6426
0.5969	0.13	1800	0.6518	0.6559
0.5992	0.14	1900	0.6544	0.6559
0.5762	0.15	2000	0.6608	0.6559
0.6483	0.16	2100	0.6436	0.6331
0.7594	0.16	2200	0.7562	0.5213
0.6423	0.17	2300	0.6326	0.6433
0.7006	0.18	2400	0.6669	0.6108
0.833	0.19	2500	0.7043	0.6559
0.6133	0.19	2600	0.6356	0.6532
0.5285	0.2	2700	0.6619	0.6606
0.7209	0.21	2800	0.7306	0.4196
0.682	0.22	2900	0.6400	0.6539
0.7148	0.22	3000	0.6421	0.6559
0.6288	0.23	3100	0.7416	0.6559
0.666	0.24	3200	0.6368	0.6293
0.772	0.25	3300	0.6973	0.4985
0.6778	0.25	3400	0.6288	0.6604
0.5939	0.26	3500	0.6566	0.6559
0.6246	0.27	3600	0.6347	0.6618
0.649	0.28	3700	0.6353	0.6277
0.7122	0.28	3800	0.6407	0.6559
0.6292	0.29	3900	0.6776	0.6560
0.6079	0.3	4000	0.6220	0.6609
0.6971	0.31	4100	0.6258	0.6394
0.7131	0.31	4200	0.7202	0.6556
0.5346	0.32	4300	0.6394	0.6571
0.5801	0.33	4400	0.6960	0.6664
0.6806	0.34	4500	0.6339	0.6348
0.6245	0.34	4600	0.6226	0.6477
0.6905	0.35	4700	0.6203	0.6533
0.741	0.36	4800	0.6464	0.6680
0.5712	0.37	4900	0.6162	0.6640
0.5566	0.37	5000	0.6182	0.6507
0.6443	0.38	5100	0.6457	0.6664
0.6107	0.39	5200	0.6092	0.6617
0.5824	0.4	5300	0.6383	0.6571
0.4775	0.4	5400	0.6606	0.6621
0.7114	0.41	5500	0.6179	0.6619
0.7701	0.42	5600	0.7982	0.4217
0.6974	0.42	5700	0.6223	0.6540
0.6669	0.43	5800	0.6249	0.6559
0.6982	0.44	5900	0.6287	0.6564
0.5811	0.45	6000	0.6104	0.6506
0.4347	0.45	6100	1.0475	0.6559
0.5885	0.46	6200	0.6125	0.6552
0.6867	0.47	6300	0.6435	0.6468
0.6088	0.48	6400	0.6047	0.6623
0.8194	0.48	6500	0.6972	0.6589
0.8182	0.49	6600	0.6053	0.6644
0.6104	0.5	6700	0.7375	0.6571
0.5552	0.51	6800	0.6231	0.6402
0.6451	0.51	6900	0.6452	0.6561
0.7849	0.52	7000	0.6177	0.6612
0.64	0.53	7100	0.6307	0.6234
0.6393	0.54	7200	0.6130	0.6554
0.8326	0.54	7300	0.7210	0.6421
0.6579	0.55	7400	0.6227	0.6544
0.5195	0.56	7500	0.6619	0.6557
0.6197	0.57	7600	0.6354	0.6498
0.8507	0.57	7700	0.6820	0.6550
0.7163	0.58	7800	0.6720	0.5328
0.6896	0.59	7900	0.6530	0.6386
0.62	0.6	8000	0.6296	0.6559
0.8254	0.6	8100	0.6752	0.6200
0.7653	0.61	8200	0.7118	0.6558
0.7742	0.62	8300	0.6262	0.6497
0.6861	0.63	8400	0.6799	0.5566
0.5652	0.63	8500	0.6708	0.6559
0.7486	0.64	8600	0.6319	0.6559
0.6204	0.65	8700	0.6407	0.6530
0.673	0.66	8800	0.7154	0.4672
0.7272	0.66	8900	0.6323	0.6528
0.7364	0.67	9000	0.6436	0.6188
0.71	0.68	9100	0.6507	0.5924
0.6767	0.69	9200	0.6347	0.6575
0.7046	0.69	9300	0.6723	0.6127
0.7486	0.7	9400	0.6328	0.6485
0.7646	0.71	9500	0.6244	0.6550
0.5971	0.72	9600	0.6610	0.6558
0.6195	0.72	9700	0.6219	0.6515
0.6891	0.73	9800	0.6300	0.6619
0.6829	0.74	9900	0.6312	0.6568
0.4786	0.75	10000	0.7160	0.6573
0.6093	0.75	10100	0.6245	0.6503
0.672	0.76	10200	0.6248	0.6577
0.6734	0.77	10300	0.6541	0.6600
0.7826	0.78	10400	0.6413	0.6559
0.6851	0.78	10500	0.6478	0.6006
0.6776	0.79	10600	0.6453	0.6175
0.7322	0.8	10700	0.6188	0.6353
0.5144	0.81	10800	0.6762	0.6571
0.6977	0.81	10900	0.6559	0.6544
0.5681	0.82	11000	0.7225	0.6559
0.6449	0.83	11100	0.6372	0.6576
0.6067	0.83	11200	0.6207	0.6391
0.5921	0.84	11300	0.6178	0.6538
0.5373	0.85	11400	0.7370	0.6559
0.6926	0.86	11500	0.6346	0.6372
0.6634	0.86	11600	0.6274	0.6489
0.61	0.87	11700	0.6309	0.6427
0.6214	0.88	11800	0.6273	0.6480
0.6202	0.89	11900	0.6255	0.6559
0.6153	0.89	12000	0.6348	0.6459
0.7062	0.9	12100	0.6283	0.6512
0.6977	0.91	12200	0.6159	0.6515
0.6041	0.92	12300	0.6251	0.6504
0.6609	0.92	12400	0.6633	0.5870
0.7565	0.93	12500	0.6200	0.6562
0.6133	0.94	12600	0.6193	0.6527
0.7066	0.95	12700	0.6279	0.6180
0.5706	0.95	12800	0.6128	0.6575
0.6992	0.96	12900	0.6334	0.6449
0.6834	0.97	13000	0.6258	0.6591
0.6069	0.98	13100	0.6290	0.6620
0.743	0.98	13200	0.6110	0.6562
0.5226	0.99	13300	0.6165	0.6557
0.7359	1.0	13400	0.6207	0.6376
0.5812	1.01	13500	0.6192	0.6559
0.666	1.01	13600	0.6347	0.6602
0.5489	1.02	13700	0.6107	0.6459
0.701	1.03	13800	0.6172	0.6518
0.4873	1.04	13900	0.6786	0.6559
0.5807	1.04	14000	0.6636	0.6433
0.6824	1.05	14100	0.6176	0.6315
0.6012	1.06	14200	0.6097	0.6617
0.4865	1.07	14300	0.6103	0.6623
0.5612	1.07	14400	0.6947	0.6559
0.5968	1.08	14500	0.6559	0.5981
0.5657	1.09	14600	0.6076	0.6509
0.4778	1.1	14700	0.6808	0.6535
0.6047	1.1	14800	0.6131	0.6480
0.5999	1.11	14900	0.6120	0.6559
0.5852	1.12	15000	0.6356	0.6553
0.7033	1.13	15100	0.6578	0.6647
0.5925	1.13	15200	0.6153	0.6633
0.5959	1.14	15300	0.6306	0.6211
0.5929	1.15	15400	0.6246	0.6655
0.5621	1.16	15500	0.6126	0.6424
0.5508	1.16	15600	0.6844	0.6559
0.6276	1.17	15700	0.6066	0.6531
1.0359	1.18	15800	0.6271	0.6617
0.6191	1.19	15900	0.6166	0.6480
0.7095	1.19	16000	0.6228	0.6462
0.6567	1.2	16100	0.6066	0.6653
0.5653	1.21	16200	0.6022	0.6605
0.6894	1.21	16300	0.6216	0.6568
0.608	1.22	16400	0.6041	0.6559
0.665	1.23	16500	0.6111	0.6564
0.6753	1.24	16600	0.6138	0.6581
0.6213	1.24	16700	0.6121	0.6380
0.6983	1.25	16800	0.6166	0.6661
0.8521	1.26	16900	0.6202	0.6461
0.4927	1.27	17000	0.6313	0.6547
0.6414	1.27	17100	0.6011	0.6667
0.539	1.28	17200	0.6451	0.6664
0.5118	1.29	17300	0.6243	0.6641
0.7512	1.3	17400	0.6257	0.6586
0.5943	1.3	17500	0.6186	0.6423
0.5861	1.31	17600	0.6435	0.6638
0.7065	1.32	17700	0.6197	0.6279
0.5973	1.33	17800	0.6081	0.6535
0.5997	1.33	17900	0.6053	0.6608
0.7091	1.34	18000	0.6013	0.6644
0.691	1.35	18100	0.6103	0.6654
0.5559	1.36	18200	0.6110	0.6658
0.6309	1.36	18300	0.6067	0.6664
0.6262	1.37	18400	0.6027	0.6616
0.5551	1.38	18500	0.6106	0.6671
0.6703	1.39	18600	0.6043	0.6576
0.6849	1.39	18700	0.6018	0.6616
0.6136	1.4	18800	0.6324	0.6629
0.7075	1.41	18900	0.6057	0.6561
0.6036	1.42	19000	0.6081	0.6559
0.6549	1.42	19100	0.6352	0.6655
0.5168	1.43	19200	0.6042	0.6632
0.5864	1.44	19300	0.6111	0.6639
0.5961	1.45	19400	0.6003	0.6644
0.6077	1.45	19500	0.6125	0.6566
0.6215	1.46	19600	0.6128	0.6582
0.4005	1.47	19700	0.6348	0.6642
0.5689	1.48	19800	0.6355	0.6647
0.6026	1.48	19900	0.6127	0.6444
0.4982	1.49	20000	0.6034	0.6654
0.6189	1.5	20100	0.6202	0.6609
0.5502	1.51	20200	0.6044	0.6621
0.5924	1.51	20300	0.6107	0.6445
0.744	1.52	20400	0.6164	0.6559
0.5582	1.53	20500	0.6166	0.6559
0.6994	1.54	20600	0.6109	0.6664
0.5396	1.54	20700	0.6189	0.6670
0.7232	1.55	20800	0.6104	0.6610
0.9802	1.56	20900	0.6232	0.6642
0.6487	1.57	21000	0.6056	0.6505
0.5932	1.57	21100	0.5980	0.6702
0.7897	1.58	21200	0.6012	0.6638
0.6006	1.59	21300	0.6232	0.6672
0.4481	1.6	21400	0.6124	0.6676
0.6078	1.6	21500	0.6495	0.6664
0.595	1.61	21600	0.7122	0.6675
0.6388	1.62	21700	0.6227	0.6671
0.5731	1.62	21800	0.6252	0.6682
0.8603	1.63	21900	0.6026	0.6653
0.6316	1.64	22000	0.6494	0.6669
0.6712	1.65	22100	0.6097	0.6676
0.6102	1.65	22200	0.6221	0.6585
0.7099	1.66	22300	0.6006	0.6658
0.621	1.67	22400	0.6026	0.6626
0.478	1.68	22500	0.6062	0.6624
0.6106	1.68	22600	0.5990	0.6669
0.5793	1.69	22700	0.5980	0.6681
0.5804	1.7	22800	0.6014	0.6626
0.6304	1.71	22900	0.6107	0.6380
0.7427	1.71	23000	0.6051	0.6682
0.5794	1.72	23100	0.6105	0.6611
0.5084	1.73	23200	0.6643	0.6673
0.6518	1.74	23300	0.6366	0.6687
0.5129	1.74	23400	0.6053	0.6682
0.7593	1.75	23500	0.5977	0.6662
0.6645	1.76	23600	0.5988	0.6683
0.6144	1.77	23700	0.6130	0.6673
0.6855	1.77	23800	0.6192	0.6596
0.559	1.78	23900	0.6208	0.6574
0.4202	1.79	24000	0.6125	0.6690
0.6604	1.8	24100	0.6052	0.6685
0.5487	1.8	24200	0.6086	0.6685
0.6816	1.81	24300	0.5997	0.6620
0.6057	1.82	24400	0.6128	0.6530
0.4335	1.83	24500	0.6121	0.6676
0.6147	1.83	24600	0.6225	0.6670
0.7414	1.84	24700	0.6248	0.6718
0.622	1.85	24800	0.6084	0.6722
0.5356	1.86	24900	0.6003	0.6611
0.7994	1.86	25000	0.6098	0.6657
0.5389	1.87	25100	0.6052	0.6633
0.6985	1.88	25200	0.6073	0.6694
0.652	1.89	25300	0.6040	0.6709
0.5409	1.89	25400	0.6065	0.6709
0.6356	1.9	25500	0.6062	0.6699
0.7588	1.91	25600	0.6025	0.6711
0.5109	1.92	25700	0.5992	0.6693
0.6766	1.92	25800	0.6004	0.6693
0.6517	1.93	25900	0.6020	0.6701
0.6561	1.94	26000	0.5995	0.6705
0.6224	1.95	26100	0.6008	0.6717
0.6054	1.95	26200	0.6005	0.6714
0.5152	1.96	26300	0.6023	0.6709
0.5503	1.97	26400	0.6032	0.6706
0.5101	1.98	26500	0.6067	0.6709
0.5229	1.98	26600	0.6079	0.6702
0.8387	1.99	26700	0.6079	0.6700
0.608	2.0	26800	0.6069	0.6699

Framework versions

• Transformers 4.30.2
• Pytorch 1.13.1+cu116
• Datasets 2.13.1
• Tokenizers 0.13.3