ASAP_FineTuningBERT_AugV6_k4_task1_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: 0.8005
• Qwk: 0.4447
• Mse: 0.8006
• Rmse: 0.8948

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.5	2	11.4835	0.0031	11.4809	3.3884
No log	1.0	4	10.4147	0.0	10.4123	3.2268
No log	1.5	6	9.4126	0.0	9.4104	3.0676
No log	2.0	8	7.9359	0.0	7.9340	2.8167
7.4197	2.5	10	6.5086	0.0	6.5071	2.5509
7.4197	3.0	12	5.2824	0.0343	5.2811	2.2981
7.4197	3.5	14	4.2079	0.0	4.2068	2.0511
7.4197	4.0	16	3.2417	0.0	3.2409	1.8003
7.4197	4.5	18	2.4790	0.0020	2.4786	1.5744
3.1152	5.0	20	1.9007	0.0790	1.9004	1.3786
3.1152	5.5	22	1.5779	0.0106	1.5779	1.2562
3.1152	6.0	24	1.1590	0.0106	1.1591	1.0766
3.1152	6.5	26	1.1179	0.0	1.1181	1.0574
3.1152	7.0	28	1.3499	0.0418	1.3500	1.1619
1.9201	7.5	30	1.2193	0.0315	1.2194	1.1043
1.9201	8.0	32	1.3668	0.0707	1.3668	1.1691
1.9201	8.5	34	1.5378	0.0910	1.5376	1.2400
1.9201	9.0	36	1.1947	0.0910	1.1947	1.0930
1.9201	9.5	38	1.1157	0.0910	1.1157	1.0562
1.6946	10.0	40	1.4371	0.1370	1.4369	1.1987
1.6946	10.5	42	1.3531	0.1461	1.3530	1.1632
1.6946	11.0	44	1.2161	0.1708	1.2160	1.1027
1.6946	11.5	46	1.7150	0.1700	1.7146	1.3094
1.6946	12.0	48	1.3266	0.1917	1.3263	1.1517
1.1766	12.5	50	0.8405	0.3473	0.8405	0.9168
1.1766	13.0	52	1.5505	0.1340	1.5500	1.2450
1.1766	13.5	54	1.3961	0.1609	1.3958	1.1814
1.1766	14.0	56	0.8375	0.3216	0.8377	0.9152
1.1766	14.5	58	1.1506	0.2009	1.1506	1.0727
0.7907	15.0	60	1.5397	0.1323	1.5395	1.2407
0.7907	15.5	62	1.0474	0.2586	1.0475	1.0235
0.7907	16.0	64	1.0456	0.2672	1.0457	1.0226
0.7907	16.5	66	1.2015	0.2448	1.2014	1.0961
0.7907	17.0	68	0.8713	0.3882	0.8715	0.9335
0.4525	17.5	70	0.8360	0.4332	0.8361	0.9144
0.4525	18.0	72	1.5594	0.2223	1.5591	1.2487
0.4525	18.5	74	1.5633	0.2321	1.5630	1.2502
0.4525	19.0	76	0.9116	0.4202	0.9115	0.9547
0.4525	19.5	78	1.1263	0.3268	1.1262	1.0612
0.2816	20.0	80	1.1964	0.3008	1.1964	1.0938
0.2816	20.5	82	0.9318	0.3697	0.9320	0.9654
0.2816	21.0	84	0.9228	0.3867	0.9230	0.9607
0.2816	21.5	86	1.4566	0.2142	1.4565	1.2068
0.2816	22.0	88	1.4263	0.2242	1.4262	1.1942
0.2454	22.5	90	0.8323	0.4256	0.8325	0.9124
0.2454	23.0	92	0.8545	0.4160	0.8548	0.9246
0.2454	23.5	94	1.0289	0.3372	1.0291	1.0145
0.2454	24.0	96	1.2086	0.2836	1.2087	1.0994
0.2454	24.5	98	0.9002	0.3607	0.9005	0.9489
0.1555	25.0	100	0.9155	0.3424	0.9158	0.9570
0.1555	25.5	102	0.9521	0.3382	0.9524	0.9759
0.1555	26.0	104	0.8685	0.3868	0.8688	0.9321
0.1555	26.5	106	1.0769	0.3192	1.0771	1.0378
0.1555	27.0	108	1.0220	0.3623	1.0222	1.0110
0.1312	27.5	110	0.8730	0.4341	0.8732	0.9345
0.1312	28.0	112	1.0125	0.3521	1.0126	1.0063
0.1312	28.5	114	0.8809	0.4061	0.8810	0.9386
0.1312	29.0	116	0.7970	0.4298	0.7972	0.8929
0.1312	29.5	118	0.8246	0.4326	0.8247	0.9082
0.1444	30.0	120	1.2542	0.2745	1.2540	1.1198
0.1444	30.5	122	1.0212	0.3503	1.0212	1.0105
0.1444	31.0	124	0.8311	0.4127	0.8314	0.9118
0.1444	31.5	126	0.8561	0.4165	0.8563	0.9254
0.1444	32.0	128	1.2465	0.2486	1.2464	1.1164
0.1611	32.5	130	1.1885	0.2524	1.1884	1.0902
0.1611	33.0	132	0.7922	0.4363	0.7924	0.8902
0.1611	33.5	134	0.7576	0.4280	0.7578	0.8705
0.1611	34.0	136	0.8807	0.3819	0.8807	0.9385
0.1611	34.5	138	1.0720	0.3151	1.0719	1.0353
0.1385	35.0	140	0.9430	0.3760	0.9431	0.9711
0.1385	35.5	142	0.8797	0.4069	0.8799	0.9380
0.1385	36.0	144	1.0303	0.3523	1.0304	1.0151
0.1385	36.5	146	1.0793	0.3215	1.0793	1.0389
0.1385	37.0	148	0.8252	0.4300	0.8254	0.9085
0.1119	37.5	150	0.8030	0.4304	0.8032	0.8962
0.1119	38.0	152	0.9167	0.3752	0.9168	0.9575
0.1119	38.5	154	0.8086	0.4473	0.8088	0.8994
0.1119	39.0	156	0.8547	0.4302	0.8548	0.9246
0.1119	39.5	158	0.8303	0.4378	0.8305	0.9113
0.0884	40.0	160	0.7510	0.4725	0.7512	0.8667
0.0884	40.5	162	0.7976	0.4568	0.7977	0.8932
0.0884	41.0	164	1.0453	0.3516	1.0453	1.0224
0.0884	41.5	166	0.8485	0.4440	0.8485	0.9212
0.0884	42.0	168	0.7102	0.5003	0.7103	0.8428
0.1091	42.5	170	0.7594	0.5019	0.7594	0.8714
0.1091	43.0	172	0.9959	0.3574	0.9959	0.9979
0.1091	43.5	174	0.8652	0.4118	0.8652	0.9302
0.1091	44.0	176	0.7537	0.4703	0.7539	0.8683
0.1091	44.5	178	0.8225	0.4275	0.8226	0.9070
0.086	45.0	180	0.8779	0.3891	0.8779	0.9370
0.086	45.5	182	0.7687	0.4497	0.7688	0.8768
0.086	46.0	184	0.7798	0.4454	0.7799	0.8831
0.086	46.5	186	0.8208	0.4375	0.8209	0.9061
0.086	47.0	188	0.7921	0.4620	0.7922	0.8901
0.0732	47.5	190	0.8044	0.4439	0.8045	0.8970
0.0732	48.0	192	0.8119	0.4343	0.8121	0.9011
0.0732	48.5	194	0.8386	0.4223	0.8387	0.9158
0.0732	49.0	196	0.8204	0.4474	0.8205	0.9058
0.0732	49.5	198	0.7661	0.4587	0.7662	0.8753
0.0638	50.0	200	0.8694	0.4040	0.8694	0.9324
0.0638	50.5	202	0.8941	0.3975	0.8941	0.9456
0.0638	51.0	204	0.7692	0.4727	0.7693	0.8771
0.0638	51.5	206	0.7720	0.4654	0.7721	0.8787
0.0638	52.0	208	0.8552	0.4289	0.8552	0.9248
0.0668	52.5	210	0.8693	0.4170	0.8693	0.9324
0.0668	53.0	212	0.7879	0.4694	0.7879	0.8876
0.0668	53.5	214	0.7668	0.4800	0.7669	0.8757
0.0668	54.0	216	0.8719	0.4350	0.8719	0.9337
0.0668	54.5	218	0.8516	0.4327	0.8516	0.9228
0.0669	55.0	220	0.7793	0.4603	0.7794	0.8828
0.0669	55.5	222	0.8153	0.4363	0.8153	0.9029
0.0669	56.0	224	0.8366	0.3964	0.8365	0.9146
0.0669	56.5	226	0.7704	0.4277	0.7705	0.8778
0.0669	57.0	228	0.7554	0.4219	0.7555	0.8692
0.0617	57.5	230	0.8023	0.4131	0.8024	0.8958
0.0617	58.0	232	0.9351	0.3522	0.9351	0.9670
0.0617	58.5	234	0.8618	0.3699	0.8619	0.9284
0.0617	59.0	236	0.7982	0.4075	0.7983	0.8935
0.0617	59.5	238	0.8351	0.3937	0.8351	0.9139
0.0696	60.0	240	0.9343	0.3639	0.9343	0.9666
0.0696	60.5	242	0.8447	0.4080	0.8447	0.9191
0.0696	61.0	244	0.7532	0.4596	0.7533	0.8679
0.0696	61.5	246	0.7610	0.4681	0.7611	0.8724
0.0696	62.0	248	0.8899	0.3779	0.8899	0.9433
0.0612	62.5	250	0.9246	0.3720	0.9245	0.9615
0.0612	63.0	252	0.8119	0.4401	0.8119	0.9011
0.0612	63.5	254	0.8015	0.4426	0.8016	0.8953
0.0612	64.0	256	0.7823	0.4321	0.7825	0.8846
0.0612	64.5	258	0.8071	0.4403	0.8073	0.8985
0.0625	65.0	260	0.9091	0.3659	0.9091	0.9535
0.0625	65.5	262	0.8511	0.3738	0.8512	0.9226
0.0625	66.0	264	0.7594	0.4740	0.7596	0.8715
0.0625	66.5	266	0.7707	0.4513	0.7708	0.8780
0.0625	67.0	268	0.8351	0.3955	0.8351	0.9139
0.0545	67.5	270	0.8569	0.3887	0.8569	0.9257
0.0545	68.0	272	0.8129	0.4379	0.8130	0.9017
0.0545	68.5	274	0.8032	0.4408	0.8033	0.8963
0.0545	69.0	276	0.8313	0.4036	0.8314	0.9118
0.0545	69.5	278	0.7664	0.4609	0.7665	0.8755
0.0449	70.0	280	0.7573	0.4847	0.7575	0.8703
0.0449	70.5	282	0.8075	0.4318	0.8075	0.8986
0.0449	71.0	284	0.8089	0.4488	0.8089	0.8994
0.0449	71.5	286	0.7777	0.4578	0.7778	0.8819
0.0449	72.0	288	0.7745	0.4621	0.7746	0.8801
0.0551	72.5	290	0.7901	0.4482	0.7902	0.8889
0.0551	73.0	292	0.7599	0.4760	0.7600	0.8718
0.0551	73.5	294	0.7329	0.4656	0.7331	0.8562
0.0551	74.0	296	0.7586	0.4775	0.7588	0.8711
0.0551	74.5	298	0.8278	0.4296	0.8279	0.9099
0.0537	75.0	300	0.7996	0.4447	0.7997	0.8943
0.0537	75.5	302	0.7602	0.4674	0.7604	0.8720
0.0537	76.0	304	0.7676	0.4620	0.7678	0.8762
0.0537	76.5	306	0.7882	0.4548	0.7884	0.8879
0.0537	77.0	308	0.7839	0.4577	0.7840	0.8854
0.0458	77.5	310	0.7574	0.4712	0.7575	0.8704
0.0458	78.0	312	0.7762	0.4587	0.7763	0.8811
0.0458	78.5	314	0.8317	0.4410	0.8318	0.9121
0.0458	79.0	316	0.8368	0.4400	0.8369	0.9148
0.0458	79.5	318	0.8111	0.4456	0.8112	0.9007
0.0434	80.0	320	0.8009	0.4528	0.8011	0.8950
0.0434	80.5	322	0.7982	0.4449	0.7984	0.8935
0.0434	81.0	324	0.8094	0.4459	0.8095	0.8997
0.0434	81.5	326	0.7980	0.4463	0.7982	0.8934
0.0434	82.0	328	0.7997	0.4463	0.7998	0.8943
0.0452	82.5	330	0.7834	0.4523	0.7836	0.8852
0.0452	83.0	332	0.7834	0.4568	0.7835	0.8852
0.0452	83.5	334	0.8143	0.4411	0.8144	0.9024
0.0452	84.0	336	0.8269	0.4328	0.8270	0.9094
0.0452	84.5	338	0.7958	0.4447	0.7959	0.8921
0.045	85.0	340	0.7833	0.4595	0.7835	0.8852
0.045	85.5	342	0.7839	0.4570	0.7840	0.8855
0.045	86.0	344	0.8145	0.4439	0.8147	0.9026
0.045	86.5	346	0.8346	0.4316	0.8347	0.9136
0.045	87.0	348	0.8149	0.4395	0.8151	0.9028
0.0438	87.5	350	0.7906	0.4543	0.7907	0.8892
0.0438	88.0	352	0.7962	0.4381	0.7963	0.8924
0.0438	88.5	354	0.8204	0.4290	0.8205	0.9058
0.0438	89.0	356	0.8268	0.4225	0.8269	0.9093
0.0438	89.5	358	0.8285	0.4290	0.8286	0.9103
0.039	90.0	360	0.8197	0.4346	0.8198	0.9054
0.039	90.5	362	0.8333	0.4328	0.8334	0.9129
0.039	91.0	364	0.8230	0.4337	0.8231	0.9073
0.039	91.5	366	0.7992	0.4441	0.7993	0.8940
0.039	92.0	368	0.7801	0.4514	0.7803	0.8833
0.0361	92.5	370	0.7794	0.4543	0.7796	0.8829
0.0361	93.0	372	0.7890	0.4514	0.7892	0.8884
0.0361	93.5	374	0.8002	0.4370	0.8004	0.8946
0.0361	94.0	376	0.8156	0.4459	0.8158	0.9032
0.0361	94.5	378	0.8295	0.4376	0.8296	0.9108
0.0418	95.0	380	0.8312	0.4398	0.8313	0.9118
0.0418	95.5	382	0.8289	0.4420	0.8290	0.9105
0.0418	96.0	384	0.8214	0.4375	0.8215	0.9064
0.0418	96.5	386	0.8063	0.4472	0.8064	0.8980
0.0418	97.0	388	0.8000	0.4373	0.8002	0.8945
0.0435	97.5	390	0.7950	0.4419	0.7952	0.8917
0.0435	98.0	392	0.7942	0.4419	0.7944	0.8913
0.0435	98.5	394	0.7961	0.4349	0.7963	0.8923
0.0435	99.0	396	0.7968	0.4349	0.7969	0.8927
0.0435	99.5	398	0.7989	0.4350	0.7991	0.8939
0.0389	100.0	400	0.8005	0.4447	0.8006	0.8948

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1