results

This model is a fine-tuned version of HooshvareLab/bert-fa-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.7347
• Precision: 0.5347
• Recall: 0.4718
• F1: 0.4704
• Accuracy: 0.4718

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: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
2.0985	0.0261	10	2.0359	0.1658	0.0730	0.0372	0.0730
2.0739	0.0522	20	1.9996	0.1472	0.0904	0.0635	0.0904
2.0404	0.0783	30	1.9585	0.1803	0.1434	0.1169	0.1434
1.9715	0.1044	40	1.9330	0.2206	0.1798	0.1338	0.1798
1.8596	0.1305	50	1.9552	0.2684	0.1738	0.0824	0.1738
1.8302	0.1567	60	2.0219	0.3429	0.1685	0.0516	0.1685
1.8838	0.1828	70	2.0038	0.1478	0.1677	0.0502	0.1677
1.9153	0.2089	80	1.9334	0.1546	0.1764	0.0823	0.1764
1.839	0.2350	90	1.9126	0.2046	0.1842	0.1002	0.1842
1.8358	0.2611	100	1.8918	0.2365	0.1972	0.1159	0.1972
1.8559	0.2872	110	1.8925	0.2209	0.2068	0.1269	0.2068
1.7707	0.3133	120	1.8970	0.2445	0.1833	0.1001	0.1833
1.7514	0.3394	130	1.9215	0.3953	0.1825	0.0943	0.1825
1.7569	0.3655	140	1.9472	0.2027	0.1746	0.0708	0.1746
1.7906	0.3916	150	1.8767	0.4575	0.2320	0.1791	0.2320
1.6752	0.4178	160	1.9244	0.4945	0.1885	0.0895	0.1885
1.7293	0.4439	170	1.8418	0.3536	0.2606	0.2013	0.2606
1.6713	0.4700	180	1.7744	0.4128	0.2702	0.2311	0.2702
1.5645	0.4961	190	1.7981	0.3822	0.2407	0.1775	0.2407
1.6074	0.5222	200	1.7513	0.4290	0.2789	0.2311	0.2789
1.4986	0.5483	210	1.7598	0.5202	0.2424	0.1861	0.2424
1.6157	0.5744	220	1.7453	0.4631	0.2798	0.2366	0.2798
1.4205	0.6005	230	1.6524	0.4198	0.3527	0.3373	0.3527
1.4854	0.6266	240	1.6375	0.4522	0.3484	0.3230	0.3484
1.4207	0.6527	250	1.6410	0.4348	0.3579	0.3279	0.3579
1.2455	0.6789	260	1.6365	0.4472	0.3588	0.3092	0.3588
1.3996	0.7050	270	1.5261	0.5027	0.4275	0.4212	0.4275
1.3084	0.7311	280	1.5914	0.4964	0.3831	0.3707	0.3831
1.3386	0.7572	290	1.5884	0.4888	0.3858	0.3633	0.3858
1.4334	0.7833	300	1.5438	0.4418	0.4231	0.4170	0.4231
1.3354	0.8094	310	1.6510	0.5115	0.3788	0.3471	0.3788
1.364	0.8355	320	1.6162	0.4985	0.3805	0.3747	0.3805
1.2291	0.8616	330	1.5523	0.4596	0.4057	0.4056	0.4057
1.2571	0.8877	340	1.5834	0.5378	0.4014	0.3990	0.4014
1.392	0.9138	350	1.4810	0.5012	0.4448	0.4413	0.4448
1.3909	0.9399	360	1.5218	0.5046	0.4301	0.4271	0.4301
1.2083	0.9661	370	1.5714	0.5127	0.4101	0.4013	0.4101
1.1827	0.9922	380	1.5607	0.5365	0.4196	0.4181	0.4196
1.2544	1.0183	390	1.4977	0.4942	0.4440	0.4392	0.4440
1.0718	1.0444	400	1.5737	0.5124	0.4257	0.4239	0.4257
1.1034	1.0705	410	1.5629	0.5218	0.4162	0.4128	0.4162
1.1171	1.0966	420	1.5049	0.4958	0.4718	0.4702	0.4718
1.1174	1.1227	430	1.5840	0.5175	0.4057	0.4019	0.4057
1.2966	1.1488	440	1.5740	0.5178	0.4214	0.4214	0.4214
1.0597	1.1749	450	1.7422	0.5221	0.3944	0.3808	0.3944
1.027	1.2010	460	1.5282	0.4853	0.4509	0.4457	0.4509
1.0327	1.2272	470	1.6277	0.4810	0.4005	0.3922	0.4005
1.127	1.2533	480	1.6321	0.4847	0.4275	0.4238	0.4275
1.1265	1.2794	490	1.6081	0.4854	0.4257	0.4148	0.4257
1.0853	1.3055	500	1.7379	0.4871	0.3884	0.3697	0.3884
1.1961	1.3316	510	1.6069	0.5028	0.4361	0.4182	0.4361
1.0534	1.3577	520	1.4849	0.5123	0.4831	0.4745	0.4831
1.1954	1.3838	530	1.6723	0.5260	0.4205	0.4078	0.4205
1.28	1.4099	540	1.8150	0.5381	0.3614	0.3311	0.3614
1.122	1.4360	550	1.4803	0.5268	0.4761	0.4738	0.4761
1.1675	1.4621	560	1.6255	0.5431	0.4170	0.4105	0.4170
1.1381	1.4883	570	1.5229	0.5410	0.4500	0.4285	0.4500
1.1103	1.5144	580	1.5931	0.5449	0.4526	0.4387	0.4526
1.0581	1.5405	590	1.5439	0.5312	0.4596	0.4504	0.4596
0.9962	1.5666	600	1.5441	0.5339	0.4579	0.4452	0.4579
1.0863	1.5927	610	1.5504	0.5364	0.4761	0.4578	0.4761
1.0893	1.6188	620	1.5631	0.5224	0.4770	0.4606	0.4770
1.1396	1.6449	630	1.5557	0.5045	0.4500	0.4469	0.4500
1.0648	1.6710	640	1.6417	0.5462	0.4431	0.4336	0.4431
1.2972	1.6971	650	1.6543	0.5509	0.4431	0.4206	0.4431
1.1413	1.7232	660	1.5779	0.5438	0.4440	0.4400	0.4440
1.076	1.7493	670	1.4805	0.5208	0.4666	0.4682	0.4666
1.1984	1.7755	680	1.5434	0.5126	0.4518	0.4482	0.4518
0.9841	1.8016	690	1.4483	0.5229	0.4865	0.4869	0.4865
1.235	1.8277	700	1.4452	0.5239	0.4935	0.4935	0.4935
1.0239	1.8538	710	1.5506	0.5414	0.4466	0.4395	0.4466
0.9993	1.8799	720	1.5191	0.5388	0.4579	0.4521	0.4579
0.8789	1.9060	730	1.5620	0.5662	0.4509	0.4497	0.4509
0.9412	1.9321	740	1.4985	0.5489	0.4726	0.4623	0.4726
1.0592	1.9582	750	1.5027	0.5366	0.4700	0.4609	0.4700
0.9971	1.9843	760	1.4782	0.5427	0.4726	0.4591	0.4726
0.9067	2.0104	770	1.4520	0.5386	0.4831	0.4790	0.4831
0.7288	2.0366	780	1.6074	0.5414	0.4474	0.4518	0.4474
0.7942	2.0627	790	1.4652	0.5256	0.4961	0.4964	0.4961
0.56	2.0888	800	1.4838	0.5312	0.4996	0.5013	0.4996
0.6195	2.1149	810	1.6563	0.5676	0.4692	0.4506	0.4692
0.6324	2.1410	820	1.7346	0.5614	0.4657	0.4666	0.4657
0.5347	2.1671	830	1.5751	0.5405	0.5065	0.5045	0.5065
0.5954	2.1932	840	1.6409	0.5521	0.4900	0.4878	0.4900
0.5179	2.2193	850	1.6171	0.5450	0.5004	0.4995	0.5004
0.5723	2.2454	860	1.6798	0.5494	0.4874	0.4861	0.4874
0.6294	2.2715	870	1.6615	0.5341	0.4857	0.4872	0.4857
0.6877	2.2977	880	1.6713	0.5305	0.4839	0.4837	0.4839
0.6666	2.3238	890	1.7254	0.5381	0.4744	0.4715	0.4744
0.6233	2.3499	900	1.6712	0.5264	0.4831	0.4805	0.4831
0.545	2.3760	910	1.6675	0.5309	0.4839	0.4808	0.4839
0.6514	2.4021	920	1.7287	0.5382	0.4692	0.4695	0.4692
0.6389	2.4282	930	1.6598	0.5237	0.4761	0.4724	0.4761
0.6108	2.4543	940	1.6726	0.5232	0.4761	0.4678	0.4761
0.6409	2.4804	950	1.6736	0.5368	0.4848	0.4782	0.4848
0.4708	2.5065	960	1.7309	0.5504	0.4787	0.4760	0.4787
0.6782	2.5326	970	1.6217	0.5280	0.4805	0.4760	0.4805
0.514	2.5587	980	1.6088	0.5196	0.4839	0.4825	0.4839
0.5716	2.5849	990	1.6967	0.5361	0.4787	0.4780	0.4787
0.5028	2.6110	1000	1.7347	0.5347	0.4718	0.4704	0.4718
0.487	2.6371	1010	1.7448	0.5275	0.4666	0.4562	0.4666
0.5283	2.6632	1020	1.7680	0.5380	0.4709	0.4567	0.4709
0.467	2.6893	1030	1.7712	0.5476	0.4735	0.4638	0.4735
0.6161	2.7154	1040	1.6711	0.5423	0.4952	0.4901	0.4952
0.5924	2.7415	1050	1.5968	0.5343	0.5056	0.5035	0.5056
0.5925	2.7676	1060	1.6077	0.5273	0.4909	0.4867	0.4909
0.5044	2.7937	1070	1.6327	0.5390	0.4917	0.4889	0.4917
0.5258	2.8198	1080	1.6310	0.5353	0.4909	0.4882	0.4909
0.6329	2.8460	1090	1.6199	0.5271	0.4865	0.4837	0.4865
0.5266	2.8721	1100	1.6065	0.5215	0.4865	0.4848	0.4865
0.5093	2.8982	1110	1.6174	0.5232	0.4874	0.4854	0.4874
0.6284	2.9243	1120	1.6325	0.5271	0.4874	0.4851	0.4874
0.4167	2.9504	1130	1.6336	0.5274	0.4865	0.4846	0.4865
0.4789	2.9765	1140	1.6295	0.5266	0.4857	0.4836	0.4857

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Tokenizers 0.19.1