dit-base-finetuned-rvlcdip-finetuned-data200

This model is a fine-tuned version of microsoft/dit-base-finetuned-rvlcdip on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 3.0080
• Accuracy: 0.5699

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: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1142	1.0	46	2.0131	0.3441
1.9953	2.0	92	1.9577	0.4086
1.9558	3.0	138	1.9231	0.4301
1.9251	4.0	184	1.8015	0.4946
1.6485	5.0	230	1.7045	0.5269
1.5973	6.0	276	1.5806	0.5054
1.4755	7.0	322	1.4849	0.5054
1.4537	8.0	368	1.4356	0.5161
1.416	9.0	414	1.4512	0.5269
1.3645	10.0	460	1.3857	0.5591
1.3017	11.0	506	1.3108	0.5484
1.2794	12.0	552	1.3027	0.5376
1.1553	13.0	598	1.2883	0.5484
1.1526	14.0	644	1.3554	0.5054
1.1116	15.0	690	1.3235	0.5914
1.1925	16.0	736	1.2401	0.5806
1.1297	17.0	782	1.3425	0.5914
0.9717	18.0	828	1.3538	0.5484
0.8404	19.0	874	1.2648	0.5699
0.7008	20.0	920	1.4971	0.5376
1.1454	21.0	966	1.4137	0.4839
0.6849	22.0	1012	1.2801	0.5591
0.8566	23.0	1058	1.2380	0.5699
0.8956	24.0	1104	1.2903	0.6129
0.8004	25.0	1150	1.4372	0.5591
0.818	26.0	1196	1.1640	0.6344
0.6387	27.0	1242	1.3120	0.6452
0.7282	28.0	1288	1.4678	0.5161
0.7426	29.0	1334	1.4815	0.5269
0.735	30.0	1380	1.2714	0.6129
0.6769	31.0	1426	1.2262	0.5699
0.5562	32.0	1472	1.3348	0.6344
0.6671	33.0	1518	1.4159	0.6129
0.3708	34.0	1564	1.6416	0.5484
0.3967	35.0	1610	1.3298	0.5699
0.4692	36.0	1656	1.3559	0.5699
0.632	37.0	1702	1.3349	0.5699
0.3719	38.0	1748	1.4697	0.5914
0.4238	39.0	1794	1.5207	0.6022
0.3608	40.0	1840	1.5557	0.5591
0.6252	41.0	1886	1.6247	0.5269
0.4183	42.0	1932	1.5885	0.5914
0.3922	43.0	1978	1.6593	0.5699
0.5715	44.0	2024	1.5270	0.5699
0.3656	45.0	2070	1.8899	0.5054
0.3656	46.0	2116	2.0936	0.4624
0.4003	47.0	2162	1.5610	0.5054
0.446	48.0	2208	1.7388	0.5376
0.5219	49.0	2254	1.4976	0.6129
0.3488	50.0	2300	1.5744	0.5914
0.323	51.0	2346	1.6312	0.6022
0.3713	52.0	2392	1.6975	0.5591
0.2981	53.0	2438	1.6229	0.5699
0.3422	54.0	2484	2.0909	0.4624
0.2538	55.0	2530	2.0966	0.5161
0.3868	56.0	2576	1.5614	0.6344
0.4662	57.0	2622	1.8929	0.5269
0.4277	58.0	2668	1.9573	0.5376
0.5301	59.0	2714	1.7999	0.5699
0.3867	60.0	2760	2.3481	0.4624
0.2334	61.0	2806	1.9924	0.5376
0.2921	62.0	2852	2.0454	0.5591
0.4386	63.0	2898	1.7798	0.5376
0.3299	64.0	2944	1.9370	0.5914
0.5982	65.0	2990	2.0527	0.5591
0.4433	66.0	3036	1.6222	0.6237
0.3717	67.0	3082	1.7977	0.5914
0.3642	68.0	3128	1.6988	0.5914
0.4541	69.0	3174	1.7567	0.6022
0.3464	70.0	3220	1.9029	0.5699
0.2764	71.0	3266	1.9611	0.6022
0.2138	72.0	3312	1.9333	0.5591
0.3928	73.0	3358	1.7701	0.5806
0.1811	74.0	3404	1.8330	0.5806
0.2076	75.0	3450	1.6676	0.6559
0.3326	76.0	3496	2.0036	0.6022
0.1343	77.0	3542	1.6937	0.6344
0.3031	78.0	3588	1.9223	0.6237
0.2743	79.0	3634	2.1681	0.5699
0.3392	80.0	3680	2.0505	0.6129
0.1346	81.0	3726	2.0190	0.5699
0.0652	82.0	3772	2.2910	0.5699
0.4219	83.0	3818	1.8858	0.5914
0.1386	84.0	3864	1.7976	0.6237
0.2155	85.0	3910	2.4278	0.5161
0.4901	86.0	3956	1.9239	0.6237
0.3141	87.0	4002	2.0954	0.6559
0.2328	88.0	4048	2.2602	0.5806
0.2768	89.0	4094	2.1083	0.5914
0.3476	90.0	4140	2.4922	0.5269
0.2029	91.0	4186	2.2094	0.5591
0.2421	92.0	4232	2.2407	0.5376
0.2034	93.0	4278	2.1488	0.5591
0.2461	94.0	4324	2.1332	0.5806
0.1462	95.0	4370	2.2702	0.5591
0.5213	96.0	4416	2.2134	0.5699
0.3634	97.0	4462	2.1066	0.5699
0.1698	98.0	4508	2.2736	0.6237
0.1685	99.0	4554	2.3919	0.5806
0.1971	100.0	4600	2.0664	0.6237
0.1496	101.0	4646	2.5661	0.5806
0.283	102.0	4692	2.0714	0.5699
0.185	103.0	4738	2.1369	0.6022
0.1489	104.0	4784	2.1653	0.6129
0.1231	105.0	4830	2.0890	0.6452
0.3224	106.0	4876	2.3771	0.5376
0.3452	107.0	4922	2.2537	0.6344
0.4404	108.0	4968	2.0253	0.6129
0.3408	109.0	5014	2.1653	0.5699
0.2406	110.0	5060	2.0196	0.6237
0.3051	111.0	5106	2.1980	0.6129
0.1515	112.0	5152	2.4104	0.5699
0.3836	113.0	5198	2.2342	0.6344
0.3572	114.0	5244	2.2321	0.6022
0.3006	115.0	5290	2.3555	0.5806
0.0965	116.0	5336	2.7237	0.4516
0.2023	117.0	5382	2.3798	0.6237
0.1272	118.0	5428	2.5357	0.5591
0.4318	119.0	5474	2.4913	0.5699
0.0414	120.0	5520	2.3760	0.6022
0.1785	121.0	5566	2.3920	0.6129
0.0142	122.0	5612	2.4256	0.6022
0.1262	123.0	5658	2.7212	0.5806
0.2219	124.0	5704	2.3683	0.5699
0.1629	125.0	5750	2.4280	0.5484
0.149	126.0	5796	3.0708	0.4839
0.2394	127.0	5842	2.2192	0.6022
0.2165	128.0	5888	2.4015	0.5806
0.0729	129.0	5934	2.2241	0.6022
0.2585	130.0	5980	2.9483	0.5054
0.1401	131.0	6026	2.3180	0.6129
0.4162	132.0	6072	3.0147	0.4946
0.1188	133.0	6118	2.3128	0.6237
0.0939	134.0	6164	2.5300	0.6022
0.1039	135.0	6210	2.5740	0.5699
0.3678	136.0	6256	2.5887	0.5914
0.3998	137.0	6302	2.5664	0.5376
0.1952	138.0	6348	2.1861	0.6774
0.2616	139.0	6394	2.7036	0.5806
0.2523	140.0	6440	2.5953	0.5806
0.2772	141.0	6486	2.4114	0.6129
0.2399	142.0	6532	2.3203	0.6237
0.3769	143.0	6578	2.7200	0.5591
0.0094	144.0	6624	2.7315	0.5591
0.1818	145.0	6670	2.5223	0.6129
0.3063	146.0	6716	2.3310	0.6237
0.222	147.0	6762	2.6180	0.5806
0.2505	148.0	6808	2.2976	0.6344
0.2705	149.0	6854	2.4091	0.5914
0.1624	150.0	6900	2.8030	0.5269
0.1322	151.0	6946	2.6379	0.5591
0.0876	152.0	6992	2.5781	0.5484
0.1332	153.0	7038	2.8476	0.5591
0.2727	154.0	7084	2.6779	0.5699
0.195	155.0	7130	3.0504	0.4839
0.152	156.0	7176	2.6103	0.5806
0.2811	157.0	7222	2.5947	0.6129
0.0742	158.0	7268	2.4666	0.6559
0.2052	159.0	7314	2.5116	0.5484
0.2598	160.0	7360	3.0400	0.5269
0.2846	161.0	7406	2.2042	0.6667
0.2653	162.0	7452	3.0598	0.5484
0.358	163.0	7498	2.7669	0.5806
0.0355	164.0	7544	2.4568	0.6237
0.1817	165.0	7590	2.9532	0.5806
0.0955	166.0	7636	2.4798	0.6237
0.1941	167.0	7682	2.7027	0.5699
0.1787	168.0	7728	2.4225	0.6237
0.0998	169.0	7774	2.5104	0.5914
0.0392	170.0	7820	2.6235	0.5806
0.2689	171.0	7866	2.9215	0.5806
0.0595	172.0	7912	2.8108	0.5699
0.148	173.0	7958	2.9213	0.5806
0.2159	174.0	8004	2.6172	0.6129
0.1221	175.0	8050	2.4386	0.6237
0.0691	176.0	8096	2.8642	0.5269
0.2014	177.0	8142	2.7364	0.6022
0.0379	178.0	8188	2.4859	0.6022
0.2202	179.0	8234	3.0665	0.5484
0.2078	180.0	8280	2.3521	0.6237
0.1051	181.0	8326	2.4827	0.6237
0.2257	182.0	8372	2.8155	0.5914
0.1339	183.0	8418	2.6274	0.6237
0.1414	184.0	8464	2.7645	0.5806
0.0993	185.0	8510	2.8886	0.5591
0.1769	186.0	8556	2.5164	0.6129
0.1575	187.0	8602	2.9346	0.5376
0.0251	188.0	8648	2.6099	0.5376
0.0536	189.0	8694	2.9630	0.5376
0.1748	190.0	8740	2.8360	0.5699
0.0151	191.0	8786	2.7525	0.6022
0.2198	192.0	8832	2.6656	0.5376
0.267	193.0	8878	3.0118	0.5591
0.1043	194.0	8924	3.0214	0.5699
0.0035	195.0	8970	2.7925	0.5806
0.0707	196.0	9016	2.7839	0.5806
0.0656	197.0	9062	3.0370	0.5376
0.1155	198.0	9108	2.6510	0.5914
0.1118	199.0	9154	2.7058	0.5699
0.3086	200.0	9200	3.0080	0.5699

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.0
• Tokenizers 0.13.2