DREsS_FineTuningBERT_Aug_organization_fold0

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5252
• Qwk: 0.5440
• Mse: 0.5505
• Rmse: 0.7420

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0588	2	9.5607	-0.0047	8.2071	2.8648
No log	0.1176	4	6.9720	0.0	6.8535	2.6179
No log	0.1765	6	5.1495	0.0	6.8535	2.6179
No log	0.2353	8	3.9024	-0.0003	2.9747	1.7247
No log	0.2941	10	2.8550	0.0	2.9343	1.7130
No log	0.3529	12	2.0817	0.0	2.9343	1.7130
No log	0.4118	14	1.4681	0.0730	0.9949	0.9975
No log	0.4706	16	1.1338	0.0	1.0152	1.0075
No log	0.5294	18	0.8412	0.0	1.0152	1.0075
No log	0.5882	20	0.7518	0.0	1.0152	1.0075
No log	0.6471	22	0.7402	0.1208	0.9596	0.9796
No log	0.7059	24	0.6887	0.2777	0.7727	0.8790
No log	0.7647	26	0.6660	0.1173	0.9040	0.9508
No log	0.8235	28	0.6295	0.2859	0.7727	0.8790
No log	0.8824	30	0.5614	0.3692	0.6717	0.8196
No log	0.9412	32	0.5379	0.3688	0.6717	0.8196
No log	1.0	34	0.6614	0.2756	0.8081	0.8989
No log	1.0588	36	0.6181	0.3015	0.7828	0.8848
No log	1.1176	38	0.5373	0.3832	0.6616	0.8134
No log	1.1765	40	0.5626	0.3848	0.6667	0.8165
No log	1.2353	42	0.5611	0.4349	0.6010	0.7752
No log	1.2941	44	0.5247	0.4425	0.5960	0.7720
No log	1.3529	46	0.5243	0.4457	0.5909	0.7687
No log	1.4118	48	0.6008	0.2930	0.7778	0.8819
No log	1.4706	50	0.6322	0.3346	0.7626	0.8733
No log	1.5294	52	0.4836	0.4485	0.5960	0.7720
No log	1.5882	54	0.5161	0.4208	0.6263	0.7914
No log	1.6471	56	0.4972	0.4457	0.6010	0.7752
No log	1.7059	58	0.5135	0.4389	0.6111	0.7817
No log	1.7647	60	0.5105	0.4301	0.6212	0.7882
No log	1.8235	62	0.4995	0.5025	0.5707	0.7555
No log	1.8824	64	0.4910	0.4694	0.6010	0.7752
No log	1.9412	66	0.5427	0.4048	0.6465	0.8040
No log	2.0	68	0.6485	0.2776	0.7828	0.8848
No log	2.0588	70	0.5999	0.3373	0.7222	0.8498
No log	2.1176	72	0.4843	0.4688	0.5859	0.7654
No log	2.1765	74	0.5521	0.4272	0.6616	0.8134
No log	2.2353	76	0.4829	0.4011	0.6414	0.8009
No log	2.2941	78	0.6287	0.2914	0.7677	0.8762
No log	2.3529	80	0.6084	0.3090	0.7475	0.8646
No log	2.4118	82	0.4905	0.3876	0.6566	0.8103
No log	2.4706	84	0.6380	0.3142	0.7980	0.8933
No log	2.5294	86	0.6256	0.3187	0.7929	0.8905
No log	2.5882	88	0.4944	0.3798	0.6667	0.8165
No log	2.6471	90	0.6242	0.2963	0.7626	0.8733
No log	2.7059	92	0.7189	0.2476	0.8182	0.9045
No log	2.7647	94	0.6084	0.3334	0.7273	0.8528
No log	2.8235	96	0.4697	0.4533	0.6162	0.7850
No log	2.8824	98	0.7257	0.3502	0.8434	0.9184
No log	2.9412	100	0.8154	0.3480	0.8889	0.9428
No log	3.0	102	0.6224	0.4153	0.7172	0.8469
No log	3.0588	104	0.4803	0.3852	0.6768	0.8227
No log	3.1176	106	0.6484	0.2683	0.7929	0.8905
No log	3.1765	108	0.7299	0.2464	0.8182	0.9045
No log	3.2353	110	0.6674	0.2552	0.8081	0.8989
No log	3.2941	112	0.5100	0.4030	0.6465	0.8040
No log	3.3529	114	0.4840	0.5031	0.5657	0.7521
No log	3.4118	116	0.5041	0.5045	0.5758	0.7588
No log	3.4706	118	0.4783	0.4614	0.6162	0.7850
No log	3.5294	120	0.4936	0.4165	0.6414	0.8009
No log	3.5882	122	0.5142	0.4130	0.6465	0.8040
No log	3.6471	124	0.4836	0.4391	0.6313	0.7946
No log	3.7059	126	0.4790	0.5044	0.5808	0.7621
No log	3.7647	128	0.4821	0.4985	0.5859	0.7654
No log	3.8235	130	0.4826	0.5187	0.5808	0.7621
No log	3.8824	132	0.4818	0.5223	0.5808	0.7621
No log	3.9412	134	0.5020	0.5179	0.5657	0.7521
No log	4.0	136	0.5724	0.4557	0.6212	0.7882
No log	4.0588	138	0.5520	0.4591	0.6263	0.7914
No log	4.1176	140	0.5188	0.5223	0.5606	0.7487
No log	4.1765	142	0.5109	0.5134	0.5707	0.7555
No log	4.2353	144	0.5153	0.5313	0.5505	0.7420
No log	4.2941	146	0.4931	0.5482	0.5556	0.7454
No log	4.3529	148	0.4866	0.5180	0.5909	0.7687
No log	4.4118	150	0.5239	0.5351	0.5556	0.7454
No log	4.4706	152	0.5760	0.5171	0.5707	0.7555
No log	4.5294	154	0.5484	0.5167	0.5657	0.7521
No log	4.5882	156	0.4877	0.4903	0.6111	0.7817
No log	4.6471	158	0.4777	0.4889	0.6111	0.7817
No log	4.7059	160	0.4746	0.4977	0.6010	0.7752
No log	4.7647	162	0.4863	0.5095	0.5707	0.7555
No log	4.8235	164	0.5206	0.4777	0.5960	0.7720
No log	4.8824	166	0.5162	0.4677	0.6061	0.7785
No log	4.9412	168	0.4963	0.4468	0.6263	0.7914
No log	5.0	170	0.4855	0.4651	0.6111	0.7817
No log	5.0588	172	0.5036	0.4854	0.5909	0.7687
No log	5.1176	174	0.5012	0.4899	0.5859	0.7654
No log	5.1765	176	0.4977	0.4899	0.5859	0.7654
No log	5.2353	178	0.5227	0.4989	0.5808	0.7621
No log	5.2941	180	0.5249	0.5031	0.5758	0.7588
No log	5.3529	182	0.4924	0.5121	0.5758	0.7588
No log	5.4118	184	0.5004	0.5083	0.5808	0.7621
No log	5.4706	186	0.5658	0.4651	0.6162	0.7850
No log	5.5294	188	0.5904	0.4483	0.6364	0.7977
No log	5.5882	190	0.5462	0.4898	0.5909	0.7687
No log	5.6471	192	0.5064	0.4991	0.6010	0.7752
No log	5.7059	194	0.4940	0.5143	0.5808	0.7621
No log	5.7647	196	0.5010	0.5260	0.5657	0.7521
No log	5.8235	198	0.5162	0.5310	0.5606	0.7487
No log	5.8824	200	0.4915	0.5490	0.5455	0.7385
No log	5.9412	202	0.4939	0.5415	0.5505	0.7420
No log	6.0	204	0.5163	0.5273	0.5657	0.7521
No log	6.0588	206	0.5067	0.5273	0.5657	0.7521
No log	6.1176	208	0.4762	0.5822	0.5101	0.7142
No log	6.1765	210	0.4715	0.5693	0.5253	0.7247
No log	6.2353	212	0.4720	0.5614	0.5303	0.7282
No log	6.2941	214	0.4860	0.5390	0.5455	0.7385
No log	6.3529	216	0.5413	0.4868	0.5960	0.7720
No log	6.4118	218	0.5423	0.4868	0.5960	0.7720
No log	6.4706	220	0.4875	0.5441	0.5404	0.7351
No log	6.5294	222	0.4644	0.5510	0.5455	0.7385
No log	6.5882	224	0.4654	0.5390	0.5606	0.7487
No log	6.6471	226	0.4762	0.5379	0.5505	0.7420
No log	6.7059	228	0.5117	0.5240	0.5606	0.7487
No log	6.7647	230	0.5250	0.5151	0.5707	0.7555
No log	6.8235	232	0.5080	0.4922	0.6061	0.7785
No log	6.8824	234	0.5064	0.5082	0.5909	0.7687
No log	6.9412	236	0.5040	0.5068	0.6061	0.7785
No log	7.0	238	0.5074	0.5120	0.5960	0.7720
No log	7.0588	240	0.5120	0.5196	0.5909	0.7687
No log	7.1176	242	0.5168	0.5196	0.5909	0.7687
No log	7.1765	244	0.5148	0.5193	0.5909	0.7687
No log	7.2353	246	0.5375	0.5093	0.5808	0.7621
No log	7.2941	248	0.5529	0.5066	0.6010	0.7752
No log	7.3529	250	0.5656	0.4990	0.6111	0.7817
No log	7.4118	252	0.5387	0.5105	0.5909	0.7687
No log	7.4706	254	0.5162	0.5249	0.5808	0.7621
No log	7.5294	256	0.5211	0.5173	0.5960	0.7720
No log	7.5882	258	0.5377	0.5154	0.6212	0.7882
No log	7.6471	260	0.5960	0.5018	0.6263	0.7914
No log	7.7059	262	0.6234	0.4618	0.6717	0.8196
No log	7.7647	264	0.5885	0.4854	0.6414	0.8009
No log	7.8235	266	0.5330	0.5106	0.5960	0.7720
No log	7.8824	268	0.5065	0.5031	0.6061	0.7785
No log	7.9412	270	0.5036	0.5266	0.5808	0.7621
No log	8.0	272	0.5074	0.5160	0.5909	0.7687
No log	8.0588	274	0.5400	0.5276	0.5657	0.7521
No log	8.1176	276	0.6023	0.4773	0.6465	0.8040
No log	8.1765	278	0.6199	0.4683	0.6465	0.8040
No log	8.2353	280	0.5897	0.5175	0.5960	0.7720
No log	8.2941	282	0.5357	0.5318	0.5859	0.7654
No log	8.3529	284	0.5024	0.5158	0.6061	0.7785
No log	8.4118	286	0.4997	0.4989	0.6162	0.7850
No log	8.4706	288	0.5061	0.5166	0.5909	0.7687
No log	8.5294	290	0.5142	0.5090	0.6010	0.7752
No log	8.5882	292	0.5301	0.5439	0.5606	0.7487
No log	8.6471	294	0.5400	0.5481	0.5556	0.7454
No log	8.7059	296	0.5318	0.5396	0.5657	0.7521
No log	8.7647	298	0.5271	0.5313	0.5657	0.7521
No log	8.8235	300	0.5241	0.5139	0.5859	0.7654
No log	8.8824	302	0.5178	0.5179	0.5808	0.7621
No log	8.9412	304	0.5225	0.5139	0.5859	0.7654
No log	9.0	306	0.5341	0.5277	0.5606	0.7487
No log	9.0588	308	0.5416	0.5029	0.5909	0.7687
No log	9.1176	310	0.5389	0.5283	0.5606	0.7487
No log	9.1765	312	0.5262	0.5309	0.5657	0.7521
No log	9.2353	314	0.5174	0.5135	0.5859	0.7654
No log	9.2941	316	0.5089	0.5086	0.5960	0.7720
No log	9.3529	318	0.5049	0.5206	0.5808	0.7621
No log	9.4118	320	0.5087	0.5129	0.5909	0.7687
No log	9.4706	322	0.5126	0.5129	0.5909	0.7687
No log	9.5294	324	0.5195	0.5345	0.5657	0.7521
No log	9.5882	326	0.5274	0.5440	0.5505	0.7420
No log	9.6471	328	0.5322	0.5483	0.5455	0.7385
No log	9.7059	330	0.5333	0.5483	0.5455	0.7385
No log	9.7647	332	0.5316	0.5483	0.5455	0.7385
No log	9.8235	334	0.5292	0.5440	0.5505	0.7420
No log	9.8824	336	0.5279	0.5440	0.5505	0.7420
No log	9.9412	338	0.5261	0.5440	0.5505	0.7420
No log	10.0	340	0.5252	0.5440	0.5505	0.7420

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1