DREsS_FineTuningBERT_Aug_organization_fold1

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: 0.6016
• Qwk: 0.4149
• Mse: 0.7020
• Rmse: 0.8379

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	9.4792	0.0002	7.3384	2.7089
No log	0.1176	4	6.8690	0.0	7.0960	2.6638
No log	0.1765	6	5.6939	-0.0015	7.0657	2.6581
No log	0.2353	8	4.0942	0.0	3.0556	1.7480
No log	0.2941	10	3.2787	0.0	3.0556	1.7480
No log	0.3529	12	2.4762	0.0	3.0556	1.7480
No log	0.4118	14	1.8910	0.0407	1.8636	1.3652
No log	0.4706	16	1.5042	0.0625	1.0	1.0
No log	0.5294	18	1.2323	0.0	1.0152	1.0075
No log	0.5882	20	0.9002	0.0	1.0152	1.0075
No log	0.6471	22	0.7866	0.0	1.0152	1.0075
No log	0.7059	24	0.7831	0.0844	0.9141	0.9561
No log	0.7647	26	0.9011	0.0	1.0152	1.0075
No log	0.8235	28	0.8440	0.0	1.0152	1.0075
No log	0.8824	30	0.7569	0.0439	0.9343	0.9666
No log	0.9412	32	0.7535	0.0389	0.9394	0.9692
No log	1.0	34	0.7828	0.0475	0.9646	0.9822
No log	1.0588	36	0.7733	0.0636	0.9444	0.9718
No log	1.1176	38	0.7886	0.0158	0.9596	0.9796
No log	1.1765	40	0.7676	0.0315	0.9444	0.9718
No log	1.2353	42	0.7199	0.2006	0.8030	0.8961
No log	1.2941	44	0.7545	0.0434	0.9697	0.9847
No log	1.3529	46	0.6980	0.3236	0.6717	0.8196
No log	1.4118	48	0.6981	0.1295	0.8535	0.9239
No log	1.4706	50	0.6871	0.2188	0.7677	0.8762
No log	1.5294	52	0.6927	0.2451	0.7576	0.8704
No log	1.5882	54	0.6963	0.2113	0.7929	0.8905
No log	1.6471	56	0.6543	0.4130	0.5808	0.7621
No log	1.7059	58	0.7086	0.1276	0.8535	0.9239
No log	1.7647	60	0.6728	0.1447	0.8384	0.9156
No log	1.8235	62	0.6356	0.3475	0.6515	0.8072
No log	1.8824	64	0.7947	0.0383	0.9747	0.9873
No log	1.9412	66	0.7659	0.0522	0.9596	0.9796
No log	2.0	68	0.6202	0.3924	0.6061	0.7785
No log	2.0588	70	0.6092	0.4118	0.5808	0.7621
No log	2.1176	72	0.5947	0.4121	0.5859	0.7654
No log	2.1765	74	0.5817	0.4107	0.5859	0.7654
No log	2.2353	76	0.5805	0.4023	0.5909	0.7687
No log	2.2941	78	0.5917	0.3604	0.6364	0.7977
No log	2.3529	80	0.6596	0.2465	0.7879	0.8876
No log	2.4118	82	0.5985	0.3216	0.7071	0.8409
No log	2.4706	84	0.5441	0.3813	0.6212	0.7882
No log	2.5294	86	0.5669	0.4173	0.5758	0.7588
No log	2.5882	88	0.5656	0.3742	0.6212	0.7882
No log	2.6471	90	0.5959	0.3563	0.6414	0.8009
No log	2.7059	92	0.6052	0.4038	0.5909	0.7687
No log	2.7647	94	0.6123	0.3548	0.6364	0.7977
No log	2.8235	96	0.5875	0.3813	0.6111	0.7817
No log	2.8824	98	0.5641	0.4403	0.5657	0.7521
No log	2.9412	100	0.5600	0.4135	0.5909	0.7687
No log	3.0	102	0.5881	0.3771	0.6263	0.7914
No log	3.0588	104	0.5452	0.4143	0.5909	0.7687
No log	3.1176	106	0.5345	0.4667	0.5505	0.7420
No log	3.1765	108	0.5384	0.4365	0.5808	0.7621
No log	3.2353	110	0.5402	0.4690	0.5758	0.7588
No log	3.2941	112	0.5764	0.4013	0.6768	0.8227
No log	3.3529	114	0.5394	0.4680	0.5707	0.7555
No log	3.4118	116	0.5438	0.4475	0.5808	0.7621
No log	3.4706	118	0.5812	0.3988	0.6667	0.8165
No log	3.5294	120	0.5802	0.3984	0.6667	0.8165
No log	3.5882	122	0.5765	0.3949	0.6162	0.7850
No log	3.6471	124	0.5780	0.4109	0.6010	0.7752
No log	3.7059	126	0.5817	0.3864	0.6414	0.8009
No log	3.7647	128	0.5861	0.3390	0.6667	0.8165
No log	3.8235	130	0.6562	0.3285	0.6667	0.8165
No log	3.8824	132	0.5960	0.3965	0.6010	0.7752
No log	3.9412	134	0.5613	0.3973	0.6162	0.7850
No log	4.0	136	0.5587	0.3996	0.6212	0.7882
No log	4.0588	138	0.5748	0.3647	0.6465	0.8040
No log	4.1176	140	0.6013	0.3534	0.6566	0.8103
No log	4.1765	142	0.5415	0.4320	0.6212	0.7882
No log	4.2353	144	0.5375	0.4606	0.5960	0.7720
No log	4.2941	146	0.5478	0.4637	0.5909	0.7687
No log	4.3529	148	0.5655	0.4254	0.6263	0.7914
No log	4.4118	150	0.5383	0.4600	0.5960	0.7720
No log	4.4706	152	0.5816	0.4535	0.6566	0.8103
No log	4.5294	154	0.5485	0.4504	0.6364	0.7977
No log	4.5882	156	0.5622	0.3967	0.6515	0.8072
No log	4.6471	158	0.5473	0.4332	0.6313	0.7946
No log	4.7059	160	0.6084	0.4212	0.7020	0.8379
No log	4.7647	162	0.5698	0.4387	0.6263	0.7914
No log	4.8235	164	0.6306	0.3848	0.6313	0.7946
No log	4.8824	166	0.6538	0.3363	0.6667	0.8165
No log	4.9412	168	0.5976	0.3730	0.6515	0.8072
No log	5.0	170	0.6059	0.3992	0.6717	0.8196
No log	5.0588	172	0.6154	0.3975	0.6869	0.8288
No log	5.1176	174	0.6018	0.3963	0.6465	0.8040
No log	5.1765	176	0.6584	0.3283	0.7020	0.8379
No log	5.2353	178	0.6209	0.4040	0.6313	0.7946
No log	5.2941	180	0.5917	0.4284	0.6364	0.7977
No log	5.3529	182	0.6039	0.4156	0.6313	0.7946
No log	5.4118	184	0.6156	0.4267	0.6061	0.7785
No log	5.4706	186	0.5685	0.4589	0.5909	0.7687
No log	5.5294	188	0.5557	0.4647	0.5909	0.7687
No log	5.5882	190	0.5556	0.4591	0.5909	0.7687
No log	5.6471	192	0.6099	0.4078	0.6263	0.7914
No log	5.7059	194	0.6094	0.4222	0.6111	0.7817
No log	5.7647	196	0.5708	0.4539	0.5909	0.7687
No log	5.8235	198	0.5911	0.4320	0.6414	0.8009
No log	5.8824	200	0.5810	0.4250	0.6414	0.8009
No log	5.9412	202	0.6304	0.3938	0.6465	0.8040
No log	6.0	204	0.7201	0.3192	0.7172	0.8469
No log	6.0588	206	0.6642	0.3330	0.6970	0.8348
No log	6.1176	208	0.5731	0.4502	0.6061	0.7785
No log	6.1765	210	0.6021	0.4477	0.6414	0.8009
No log	6.2353	212	0.5796	0.4170	0.6515	0.8072
No log	6.2941	214	0.5995	0.4407	0.6313	0.7946
No log	6.3529	216	0.6434	0.4069	0.6616	0.8134
No log	6.4118	218	0.5940	0.4457	0.6313	0.7946
No log	6.4706	220	0.5628	0.4613	0.6061	0.7785
No log	6.5294	222	0.5626	0.4569	0.6111	0.7817
No log	6.5882	224	0.5813	0.4638	0.6111	0.7817
No log	6.6471	226	0.6599	0.3837	0.6869	0.8288
No log	6.7059	228	0.6420	0.3743	0.6919	0.8318
No log	6.7647	230	0.5790	0.4539	0.6010	0.7752
No log	6.8235	232	0.5757	0.4368	0.6212	0.7882
No log	6.8824	234	0.5842	0.4402	0.6111	0.7817
No log	6.9412	236	0.6027	0.4537	0.6010	0.7752
No log	7.0	238	0.6042	0.4496	0.6111	0.7817
No log	7.0588	240	0.5906	0.4163	0.6313	0.7946
No log	7.1176	242	0.5879	0.4326	0.6313	0.7946
No log	7.1765	244	0.5910	0.4215	0.6313	0.7946
No log	7.2353	246	0.6175	0.4524	0.5909	0.7687
No log	7.2941	248	0.6068	0.4385	0.6061	0.7785
No log	7.3529	250	0.5871	0.4492	0.6061	0.7785
No log	7.4118	252	0.5799	0.4379	0.6263	0.7914
No log	7.4706	254	0.5795	0.4453	0.6111	0.7817
No log	7.5294	256	0.6141	0.4197	0.6313	0.7946
No log	7.5882	258	0.6342	0.3947	0.6515	0.8072
No log	7.6471	260	0.6011	0.4214	0.6414	0.8009
No log	7.7059	262	0.5738	0.4731	0.5909	0.7687
No log	7.7647	264	0.5713	0.4601	0.6061	0.7785
No log	7.8235	266	0.5798	0.4638	0.6111	0.7817
No log	7.8824	268	0.5788	0.4638	0.6111	0.7817
No log	7.9412	270	0.5754	0.4562	0.6263	0.7914
No log	8.0	272	0.5842	0.4638	0.6111	0.7817
No log	8.0588	274	0.6024	0.4096	0.6717	0.8196
No log	8.1176	276	0.6002	0.4135	0.6616	0.8134
No log	8.1765	278	0.5810	0.4557	0.6212	0.7882
No log	8.2353	280	0.5952	0.4545	0.6263	0.7914
No log	8.2941	282	0.6188	0.4275	0.6768	0.8227
No log	8.3529	284	0.6033	0.4551	0.6263	0.7914
No log	8.4118	286	0.5848	0.4340	0.6414	0.8009
No log	8.4706	288	0.6111	0.4057	0.6465	0.8040
No log	8.5294	290	0.6437	0.4157	0.6465	0.8040
No log	8.5882	292	0.6349	0.4258	0.6414	0.8009
No log	8.6471	294	0.6060	0.4274	0.6465	0.8040
No log	8.7059	296	0.5994	0.4457	0.6263	0.7914
No log	8.7647	298	0.5973	0.4508	0.6263	0.7914
No log	8.8235	300	0.5939	0.4435	0.6414	0.8009
No log	8.8824	302	0.5992	0.4620	0.6212	0.7882
No log	8.9412	304	0.6000	0.4665	0.6313	0.7946
No log	9.0	306	0.6020	0.4306	0.6616	0.8134
No log	9.0588	308	0.6138	0.4475	0.6515	0.8072
No log	9.1176	310	0.6160	0.4430	0.6566	0.8103
No log	9.1765	312	0.6116	0.4517	0.6465	0.8040
No log	9.2353	314	0.6061	0.4348	0.6667	0.8165
No log	9.2941	316	0.6048	0.4348	0.6667	0.8165
No log	9.3529	318	0.6042	0.4268	0.6818	0.8257
No log	9.4118	320	0.6109	0.4269	0.6869	0.8288
No log	9.4706	322	0.6169	0.4318	0.6919	0.8318
No log	9.5294	324	0.6228	0.4168	0.7273	0.8528
No log	9.5882	326	0.6196	0.4209	0.7222	0.8498
No log	9.6471	328	0.6184	0.4209	0.7222	0.8498
No log	9.7059	330	0.6160	0.4257	0.7222	0.8498
No log	9.7647	332	0.6112	0.4284	0.7020	0.8379
No log	9.8235	334	0.6064	0.4244	0.7071	0.8409
No log	9.8824	336	0.6032	0.4237	0.6970	0.8348
No log	9.9412	338	0.6021	0.4232	0.6919	0.8318
No log	10.0	340	0.6016	0.4149	0.7020	0.8379

Framework versions

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