ASAP_FineTuningBERT_Aug_k1_task1_organization_fold4

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: 0.5265
• Qwk: 0.6796
• Mse: 0.5265
• Rmse: 0.7256

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	0.0417	2	11.2699	0.0	11.2699	3.3571
No log	0.0833	4	9.3623	0.0	9.3623	3.0598
No log	0.125	6	8.1887	0.0180	8.1887	2.8616
No log	0.1667	8	6.7371	0.0041	6.7371	2.5956
No log	0.2083	10	5.1276	0.0018	5.1276	2.2644
No log	0.25	12	3.8558	0.0271	3.8558	1.9636
No log	0.2917	14	3.0311	0.0144	3.0311	1.7410
No log	0.3333	16	2.0260	0.0118	2.0260	1.4234
No log	0.375	18	1.3929	0.1339	1.3929	1.1802
No log	0.4167	20	1.0161	0.0482	1.0161	1.0080
No log	0.4583	22	0.8732	0.0420	0.8732	0.9344
No log	0.5	24	0.8395	0.0420	0.8395	0.9162
No log	0.5417	26	0.8377	0.0420	0.8377	0.9152
No log	0.5833	28	0.7499	0.0420	0.7499	0.8659
No log	0.625	30	0.7141	0.0445	0.7141	0.8450
No log	0.6667	32	0.6710	0.1672	0.6710	0.8191
No log	0.7083	34	0.7725	0.3880	0.7725	0.8789
No log	0.75	36	0.6588	0.5275	0.6588	0.8116
No log	0.7917	38	0.5369	0.3533	0.5369	0.7327
No log	0.8333	40	0.5147	0.4978	0.5147	0.7174
No log	0.875	42	0.5289	0.5851	0.5289	0.7273
No log	0.9167	44	0.4616	0.5053	0.4616	0.6794
No log	0.9583	46	0.4515	0.5436	0.4515	0.6720
No log	1.0	48	0.6819	0.5619	0.6819	0.8258
No log	1.0417	50	0.6219	0.5921	0.6219	0.7886
No log	1.0833	52	0.4424	0.5574	0.4424	0.6651
No log	1.125	54	0.4527	0.5123	0.4527	0.6728
No log	1.1667	56	0.5569	0.5981	0.5569	0.7463
No log	1.2083	58	0.6383	0.5822	0.6383	0.7989
No log	1.25	60	0.5338	0.5972	0.5338	0.7306
No log	1.2917	62	0.5950	0.5800	0.5950	0.7714
No log	1.3333	64	0.4756	0.5967	0.4756	0.6897
No log	1.375	66	0.4338	0.5528	0.4338	0.6587
No log	1.4167	68	0.4640	0.6126	0.4640	0.6812
No log	1.4583	70	0.6271	0.5856	0.6271	0.7919
No log	1.5	72	0.4851	0.6024	0.4851	0.6965
No log	1.5417	74	0.4734	0.4620	0.4734	0.6880
No log	1.5833	76	0.5325	0.4431	0.5325	0.7297
No log	1.625	78	0.4280	0.5707	0.4280	0.6542
No log	1.6667	80	0.5599	0.5865	0.5599	0.7483
No log	1.7083	82	0.8027	0.5234	0.8027	0.8959
No log	1.75	84	0.6785	0.5532	0.6785	0.8237
No log	1.7917	86	0.4635	0.5671	0.4635	0.6808
No log	1.8333	88	0.4464	0.5372	0.4464	0.6682
No log	1.875	90	0.4805	0.6042	0.4805	0.6932
No log	1.9167	92	0.5107	0.6076	0.5107	0.7147
No log	1.9583	94	0.4286	0.5905	0.4286	0.6547
No log	2.0	96	0.4261	0.5733	0.4261	0.6528
No log	2.0417	98	0.4704	0.6098	0.4704	0.6858
No log	2.0833	100	0.5118	0.6168	0.5118	0.7154
No log	2.125	102	0.4913	0.6260	0.4913	0.7009
No log	2.1667	104	0.4274	0.5708	0.4274	0.6537
No log	2.2083	106	0.4409	0.5729	0.4409	0.6640
No log	2.25	108	0.4875	0.6479	0.4875	0.6982
No log	2.2917	110	0.7495	0.6007	0.7495	0.8658
No log	2.3333	112	0.6463	0.6235	0.6463	0.8039
No log	2.375	114	0.4544	0.6216	0.4544	0.6741
No log	2.4167	116	0.4329	0.6018	0.4329	0.6579
No log	2.4583	118	0.4995	0.6310	0.4995	0.7067
No log	2.5	120	0.5789	0.6167	0.5789	0.7609
No log	2.5417	122	0.4697	0.6588	0.4697	0.6853
No log	2.5833	124	0.4827	0.6502	0.4827	0.6948
No log	2.625	126	0.4584	0.6568	0.4584	0.6770
No log	2.6667	128	0.4117	0.5831	0.4117	0.6416
No log	2.7083	130	0.4084	0.5604	0.4084	0.6390
No log	2.75	132	0.4560	0.6203	0.4560	0.6753
No log	2.7917	134	0.5400	0.6037	0.5400	0.7349
No log	2.8333	136	0.4389	0.6169	0.4389	0.6625
No log	2.875	138	0.4256	0.5317	0.4256	0.6523
No log	2.9167	140	0.4140	0.5786	0.4140	0.6434
No log	2.9583	142	0.4362	0.6323	0.4362	0.6605
No log	3.0	144	0.5926	0.6655	0.5926	0.7698
No log	3.0417	146	0.6280	0.6651	0.6280	0.7925
No log	3.0833	148	0.4395	0.6750	0.4395	0.6629
No log	3.125	150	0.4740	0.4927	0.4740	0.6884
No log	3.1667	152	0.4862	0.4892	0.4862	0.6973
No log	3.2083	154	0.4042	0.5827	0.4042	0.6358
No log	3.25	156	0.5375	0.6708	0.5375	0.7332
No log	3.2917	158	0.5542	0.6797	0.5542	0.7444
No log	3.3333	160	0.4328	0.6458	0.4328	0.6579
No log	3.375	162	0.4086	0.5605	0.4086	0.6393
No log	3.4167	164	0.4055	0.5936	0.4055	0.6368
No log	3.4583	166	0.4671	0.6441	0.4671	0.6834
No log	3.5	168	0.5957	0.6802	0.5957	0.7718
No log	3.5417	170	0.5395	0.6554	0.5395	0.7345
No log	3.5833	172	0.4185	0.6185	0.4185	0.6469
No log	3.625	174	0.4139	0.6134	0.4139	0.6433
No log	3.6667	176	0.4666	0.6358	0.4666	0.6831
No log	3.7083	178	0.5023	0.6492	0.5023	0.7088
No log	3.75	180	0.4782	0.6300	0.4782	0.6915
No log	3.7917	182	0.4436	0.6304	0.4436	0.6661
No log	3.8333	184	0.4366	0.6488	0.4366	0.6608
No log	3.875	186	0.5210	0.6807	0.5210	0.7218
No log	3.9167	188	0.5182	0.6587	0.5182	0.7198
No log	3.9583	190	0.5036	0.6476	0.5036	0.7097
No log	4.0	192	0.4960	0.6579	0.4960	0.7042
No log	4.0417	194	0.5929	0.6485	0.5929	0.7700
No log	4.0833	196	0.5575	0.6530	0.5575	0.7467
No log	4.125	198	0.4605	0.6801	0.4605	0.6786
No log	4.1667	200	0.4428	0.6622	0.4428	0.6655
No log	4.2083	202	0.4125	0.6240	0.4125	0.6422
No log	4.25	204	0.4836	0.6366	0.4836	0.6954
No log	4.2917	206	0.4626	0.6324	0.4626	0.6801
No log	4.3333	208	0.3992	0.5814	0.3992	0.6318
No log	4.375	210	0.4001	0.5947	0.4001	0.6326
No log	4.4167	212	0.4443	0.6581	0.4443	0.6666
No log	4.4583	214	0.6292	0.6739	0.6292	0.7932
No log	4.5	216	0.6411	0.6842	0.6411	0.8007
No log	4.5417	218	0.4523	0.6746	0.4523	0.6725
No log	4.5833	220	0.4365	0.6559	0.4365	0.6607
No log	4.625	222	0.5204	0.7094	0.5204	0.7214
No log	4.6667	224	0.5400	0.7061	0.5400	0.7349
No log	4.7083	226	0.4752	0.6921	0.4752	0.6894
No log	4.75	228	0.4147	0.6517	0.4147	0.6439
No log	4.7917	230	0.4137	0.6395	0.4137	0.6432
No log	4.8333	232	0.4862	0.6878	0.4862	0.6973
No log	4.875	234	0.6432	0.7126	0.6432	0.8020
No log	4.9167	236	0.5727	0.6960	0.5727	0.7568
No log	4.9583	238	0.5123	0.6841	0.5123	0.7158
No log	5.0	240	0.5227	0.6835	0.5227	0.7230
No log	5.0417	242	0.5506	0.7064	0.5506	0.7420
No log	5.0833	244	0.5198	0.6969	0.5198	0.7209
No log	5.125	246	0.5042	0.6892	0.5042	0.7101
No log	5.1667	248	0.4455	0.6430	0.4455	0.6675
No log	5.2083	250	0.4406	0.6427	0.4406	0.6638
No log	5.25	252	0.5149	0.6982	0.5149	0.7175
No log	5.2917	254	0.6948	0.7113	0.6948	0.8335
No log	5.3333	256	0.5962	0.7054	0.5962	0.7721
No log	5.375	258	0.4454	0.6847	0.4454	0.6674
No log	5.4167	260	0.4209	0.6550	0.4209	0.6488
No log	5.4583	262	0.4701	0.6843	0.4701	0.6856
No log	5.5	264	0.4978	0.6908	0.4978	0.7056
No log	5.5417	266	0.4894	0.6863	0.4894	0.6995
No log	5.5833	268	0.4603	0.6817	0.4603	0.6785
No log	5.625	270	0.4820	0.6902	0.4820	0.6943
No log	5.6667	272	0.5136	0.6898	0.5136	0.7166
No log	5.7083	274	0.5029	0.6875	0.5029	0.7091
No log	5.75	276	0.5700	0.7031	0.5700	0.7550
No log	5.7917	278	0.5115	0.6824	0.5115	0.7152
No log	5.8333	280	0.4894	0.6796	0.4894	0.6995
No log	5.875	282	0.4605	0.6644	0.4605	0.6786
No log	5.9167	284	0.5142	0.6865	0.5142	0.7171
No log	5.9583	286	0.5051	0.6882	0.5051	0.7107
No log	6.0	288	0.4478	0.6527	0.4478	0.6691
No log	6.0417	290	0.4523	0.6629	0.4523	0.6725
No log	6.0833	292	0.4948	0.6797	0.4948	0.7034
No log	6.125	294	0.4783	0.6738	0.4783	0.6916
No log	6.1667	296	0.4427	0.6364	0.4427	0.6654
No log	6.2083	298	0.4681	0.6697	0.4681	0.6842
No log	6.25	300	0.5424	0.6850	0.5424	0.7365
No log	6.2917	302	0.5472	0.6816	0.5472	0.7397
No log	6.3333	304	0.5363	0.6838	0.5363	0.7324
No log	6.375	306	0.4842	0.6722	0.4842	0.6958
No log	6.4167	308	0.5191	0.6820	0.5191	0.7205
No log	6.4583	310	0.4887	0.6720	0.4887	0.6990
No log	6.5	312	0.5196	0.6782	0.5196	0.7208
No log	6.5417	314	0.5751	0.6875	0.5751	0.7583
No log	6.5833	316	0.6437	0.7039	0.6437	0.8023
No log	6.625	318	0.5994	0.6922	0.5994	0.7742
No log	6.6667	320	0.4869	0.6814	0.4869	0.6978
No log	6.7083	322	0.5094	0.6849	0.5094	0.7137
No log	6.75	324	0.4909	0.6798	0.4909	0.7007
No log	6.7917	326	0.4471	0.6578	0.4471	0.6686
No log	6.8333	328	0.4749	0.6835	0.4749	0.6891
No log	6.875	330	0.5589	0.6901	0.5589	0.7476
No log	6.9167	332	0.5669	0.6828	0.5669	0.7529
No log	6.9583	334	0.4628	0.6640	0.4628	0.6803
No log	7.0	336	0.4375	0.6543	0.4375	0.6614
No log	7.0417	338	0.4359	0.6435	0.4359	0.6602
No log	7.0833	340	0.5039	0.6754	0.5039	0.7099
No log	7.125	342	0.5382	0.6784	0.5382	0.7336
No log	7.1667	344	0.4983	0.6808	0.4983	0.7059
No log	7.2083	346	0.4702	0.6701	0.4702	0.6857
No log	7.25	348	0.5240	0.6862	0.5240	0.7239
No log	7.2917	350	0.5335	0.6880	0.5335	0.7304
No log	7.3333	352	0.5482	0.6843	0.5482	0.7404
No log	7.375	354	0.6141	0.7026	0.6141	0.7836
No log	7.4167	356	0.5839	0.6906	0.5839	0.7641
No log	7.4583	358	0.5058	0.6788	0.5058	0.7112
No log	7.5	360	0.4728	0.6761	0.4728	0.6876
No log	7.5417	362	0.4994	0.6881	0.4994	0.7067
No log	7.5833	364	0.5384	0.6834	0.5384	0.7338
No log	7.625	366	0.5037	0.6819	0.5037	0.7097
No log	7.6667	368	0.4643	0.6677	0.4643	0.6814
No log	7.7083	370	0.4606	0.6717	0.4606	0.6786
No log	7.75	372	0.5266	0.6831	0.5266	0.7257
No log	7.7917	374	0.6326	0.6992	0.6326	0.7954
No log	7.8333	376	0.6051	0.6874	0.6051	0.7779
No log	7.875	378	0.4921	0.6761	0.4921	0.7015
No log	7.9167	380	0.4477	0.6435	0.4477	0.6691
No log	7.9583	382	0.4435	0.6280	0.4435	0.6660
No log	8.0	384	0.4709	0.6682	0.4709	0.6862
No log	8.0417	386	0.5734	0.6758	0.5734	0.7573
No log	8.0833	388	0.5860	0.6824	0.5860	0.7655
No log	8.125	390	0.5144	0.6846	0.5144	0.7172
No log	8.1667	392	0.4603	0.6754	0.4603	0.6785
No log	8.2083	394	0.4504	0.6672	0.4504	0.6711
No log	8.25	396	0.4701	0.6767	0.4701	0.6857
No log	8.2917	398	0.5024	0.6797	0.5024	0.7088
No log	8.3333	400	0.5424	0.6794	0.5424	0.7364
No log	8.375	402	0.5483	0.6769	0.5483	0.7405
No log	8.4167	404	0.5185	0.6716	0.5185	0.7201
No log	8.4583	406	0.5112	0.6727	0.5112	0.7150
No log	8.5	408	0.4790	0.6600	0.4790	0.6921
No log	8.5417	410	0.4861	0.6663	0.4861	0.6972
No log	8.5833	412	0.5152	0.6710	0.5152	0.7177
No log	8.625	414	0.5023	0.6771	0.5023	0.7087
No log	8.6667	416	0.4809	0.6668	0.4809	0.6935
No log	8.7083	418	0.4814	0.6685	0.4814	0.6938
No log	8.75	420	0.5047	0.6774	0.5047	0.7105
No log	8.7917	422	0.5499	0.6805	0.5499	0.7416
No log	8.8333	424	0.6000	0.6923	0.6000	0.7746
No log	8.875	426	0.5724	0.6806	0.5724	0.7566
No log	8.9167	428	0.5124	0.6724	0.5124	0.7158
No log	8.9583	430	0.4805	0.6731	0.4805	0.6932
No log	9.0	432	0.4820	0.6727	0.4820	0.6943
No log	9.0417	434	0.4850	0.6722	0.4850	0.6964
No log	9.0833	436	0.5131	0.6734	0.5131	0.7163
No log	9.125	438	0.5370	0.6799	0.5370	0.7328
No log	9.1667	440	0.5264	0.6727	0.5264	0.7255
No log	9.2083	442	0.5091	0.6783	0.5091	0.7135
No log	9.25	444	0.5087	0.6783	0.5087	0.7132
No log	9.2917	446	0.5293	0.6724	0.5293	0.7276
No log	9.3333	448	0.5697	0.6837	0.5697	0.7548
No log	9.375	450	0.6115	0.6924	0.6115	0.7820
No log	9.4167	452	0.6218	0.7042	0.6218	0.7885
No log	9.4583	454	0.5979	0.6893	0.5979	0.7732
No log	9.5	456	0.5560	0.6776	0.5560	0.7457
No log	9.5417	458	0.5147	0.6813	0.5147	0.7174
No log	9.5833	460	0.4869	0.6781	0.4869	0.6978
No log	9.625	462	0.4784	0.6722	0.4784	0.6916
No log	9.6667	464	0.4805	0.6735	0.4805	0.6932
No log	9.7083	466	0.4818	0.6747	0.4818	0.6941
No log	9.75	468	0.4894	0.6735	0.4894	0.6996
No log	9.7917	470	0.4987	0.6709	0.4987	0.7062
No log	9.8333	472	0.5104	0.6770	0.5104	0.7144
No log	9.875	474	0.5188	0.6807	0.5188	0.7203
No log	9.9167	476	0.5244	0.6787	0.5244	0.7242
No log	9.9583	478	0.5257	0.6796	0.5257	0.7251
No log	10.0	480	0.5265	0.6796	0.5265	0.7256

Framework versions

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