ASAP_FineTuningBERT_AugV5_k3_task1_organization_fold2

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: 1.6350
• Qwk: 0.0231
• Mse: 1.6358
• Rmse: 1.2790

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	0.6667	2	10.6776	0.0053	10.6773	3.2676
No log	1.3333	4	9.6584	0.0	9.6582	3.1078
No log	2.0	6	8.0731	0.0	8.0729	2.8413
No log	2.6667	8	6.2575	-0.0002	6.2573	2.5015
5.7197	3.3333	10	4.5734	0.0078	4.5733	2.1385
5.7197	4.0	12	3.4588	0.0	3.4589	1.8598
5.7197	4.6667	14	2.5682	0.0585	2.5684	1.6026
5.7197	5.3333	16	1.7364	0.0677	1.7365	1.3178
5.7197	6.0	18	1.7835	0.0257	1.7838	1.3356
1.9116	6.6667	20	2.0227	0.0403	2.0230	1.4223
1.9116	7.3333	22	1.8080	0.0192	1.8082	1.3447
1.9116	8.0	24	1.3627	0.0107	1.3629	1.1674
1.9116	8.6667	26	1.5512	0.0107	1.5514	1.2456
1.9116	9.3333	28	1.6988	0.0174	1.6990	1.3035
1.8858	10.0	30	1.8267	0.0466	1.8269	1.3516
1.8858	10.6667	32	1.8717	0.0454	1.8719	1.3682
1.8858	11.3333	34	1.6450	0.0349	1.6452	1.2827
1.8858	12.0	36	1.3104	0.0107	1.3106	1.1448
1.8858	12.6667	38	1.5374	0.0491	1.5376	1.2400
1.6052	13.3333	40	2.2800	0.0388	2.2803	1.5101
1.6052	14.0	42	1.9449	0.0670	1.9452	1.3947
1.6052	14.6667	44	1.2323	0.0107	1.2327	1.1103
1.6052	15.3333	46	1.1505	0.0	1.1509	1.0728
1.6052	16.0	48	1.7654	0.0507	1.7660	1.3289
1.429	16.6667	50	2.1183	-0.0005	2.1191	1.4557
1.429	17.3333	52	2.2957	-0.0026	2.2967	1.5155
1.429	18.0	54	1.1098	0.0662	1.1103	1.0537
1.429	18.6667	56	1.0314	0.1392	1.0319	1.0158
1.429	19.3333	58	2.2284	-0.0068	2.2293	1.4931
0.9294	20.0	60	2.6028	-0.0152	2.6038	1.6136
0.9294	20.6667	62	1.1656	0.0970	1.1662	1.0799
0.9294	21.3333	64	0.9419	0.1628	0.9424	0.9708
0.9294	22.0	66	1.6367	0.0425	1.6372	1.2795
0.9294	22.6667	68	1.8437	0.0518	1.8443	1.3581
0.7127	23.3333	70	1.6525	0.0670	1.6532	1.2858
0.7127	24.0	72	1.3043	0.1307	1.3052	1.1424
0.7127	24.6667	74	1.9452	0.0551	1.9465	1.3952
0.7127	25.3333	76	2.4381	0.0213	2.4396	1.5619
0.7127	26.0	78	1.1106	0.1370	1.1113	1.0542
0.3668	26.6667	80	1.0245	0.1503	1.0250	1.0124
0.3668	27.3333	82	2.1971	0.0312	2.1977	1.4825
0.3668	28.0	84	2.6842	0.0187	2.6847	1.6385
0.3668	28.6667	86	1.4333	0.1130	1.4337	1.1974
0.3668	29.3333	88	0.8502	0.2100	0.8506	0.9223
0.4568	30.0	90	0.9749	0.1675	0.9753	0.9876
0.4568	30.6667	92	2.2086	0.0165	2.2092	1.4863
0.4568	31.3333	94	3.1041	-0.0050	3.1047	1.7620
0.4568	32.0	96	2.0165	0.0256	2.0170	1.4202
0.4568	32.6667	98	1.1154	0.1198	1.1158	1.0563
0.3555	33.3333	100	1.2009	0.1115	1.2013	1.0960
0.3555	34.0	102	2.1893	0.0266	2.1898	1.4798
0.3555	34.6667	104	2.3605	0.0126	2.3611	1.5366
0.3555	35.3333	106	1.4395	0.0934	1.4401	1.2000
0.3555	36.0	108	1.2613	0.1159	1.2620	1.1234
0.2402	36.6667	110	2.0099	0.0293	2.0108	1.4180
0.2402	37.3333	112	2.1534	0.0288	2.1544	1.4678
0.2402	38.0	114	1.2821	0.1390	1.2829	1.1327
0.2402	38.6667	116	1.1801	0.1393	1.1809	1.0867
0.2402	39.3333	118	1.8533	0.0535	1.8542	1.3617
0.2142	40.0	120	2.0515	0.0336	2.0524	1.4326
0.2142	40.6667	122	1.3143	0.1374	1.3150	1.1467
0.2142	41.3333	124	1.2383	0.1412	1.2390	1.1131
0.2142	42.0	126	1.8776	0.0621	1.8783	1.3705
0.2142	42.6667	128	1.9049	0.0524	1.9055	1.3804
0.1439	43.3333	130	1.4200	0.0828	1.4207	1.1919
0.1439	44.0	132	1.6179	0.0593	1.6187	1.2723
0.1439	44.6667	134	2.0902	0.0078	2.0910	1.4460
0.1439	45.3333	136	1.7861	0.0394	1.7869	1.3368
0.1439	46.0	138	1.2555	0.0945	1.2562	1.1208
0.1369	46.6667	140	1.4760	0.0500	1.4768	1.2153
0.1369	47.3333	142	2.0689	0.0107	2.0698	1.4387
0.1369	48.0	144	1.9455	0.0218	1.9465	1.3952
0.1369	48.6667	146	1.2911	0.0858	1.2919	1.1366
0.1369	49.3333	148	1.0887	0.1198	1.0893	1.0437
0.1239	50.0	150	1.3433	0.0692	1.3440	1.1593
0.1239	50.6667	152	2.1301	0.0243	2.1308	1.4597
0.1239	51.3333	154	2.2765	0.0132	2.2772	1.5090
0.1239	52.0	156	1.6208	0.0387	1.6215	1.2734
0.1239	52.6667	158	1.3080	0.0905	1.3086	1.1439
0.1216	53.3333	160	1.5683	0.0510	1.5690	1.2526
0.1216	54.0	162	2.2286	0.0142	2.2293	1.4931
0.1216	54.6667	164	2.1217	0.0210	2.1223	1.4568
0.1216	55.3333	166	1.4775	0.0592	1.4782	1.2158
0.1216	56.0	168	1.2821	0.1022	1.2829	1.1326
0.1233	56.6667	170	1.5417	0.0591	1.5424	1.2419
0.1233	57.3333	172	1.9744	0.0193	1.9751	1.4054
0.1233	58.0	174	1.7540	0.0203	1.7547	1.3247
0.1233	58.6667	176	1.4000	0.0517	1.4007	1.1835
0.1233	59.3333	178	1.5599	0.0486	1.5607	1.2493
0.0843	60.0	180	1.8944	0.0218	1.8952	1.3766
0.0843	60.6667	182	1.7514	0.0288	1.7521	1.3237
0.0843	61.3333	184	1.5121	0.0417	1.5128	1.2299
0.0843	62.0	186	1.5184	0.0352	1.5191	1.2325
0.0843	62.6667	188	1.7764	0.0183	1.7771	1.3331
0.067	63.3333	190	1.8498	0.0086	1.8505	1.3603
0.067	64.0	192	1.5320	0.0320	1.5326	1.2380
0.067	64.6667	194	1.5265	0.0244	1.5272	1.2358
0.067	65.3333	196	1.6956	0.0212	1.6962	1.3024
0.067	66.0	198	1.5750	0.0455	1.5756	1.2552
0.0939	66.6667	200	1.6177	0.0396	1.6183	1.2721
0.0939	67.3333	202	1.5220	0.0468	1.5226	1.2339
0.0939	68.0	204	1.7128	0.0348	1.7135	1.3090
0.0939	68.6667	206	1.9817	0.0365	1.9824	1.4080
0.0939	69.3333	208	1.7176	0.0386	1.7183	1.3108
0.0893	70.0	210	1.3721	0.0592	1.3728	1.1717
0.0893	70.6667	212	1.4323	0.0479	1.4330	1.1971
0.0893	71.3333	214	1.6648	0.0414	1.6654	1.2905
0.0893	72.0	216	1.5868	0.0231	1.5875	1.2600
0.0893	72.6667	218	1.3284	0.0744	1.3292	1.1529
0.0688	73.3333	220	1.2438	0.1206	1.2446	1.1156
0.0688	74.0	222	1.4085	0.0761	1.4093	1.1871
0.0688	74.6667	224	1.8282	0.0285	1.8290	1.3524
0.0688	75.3333	226	2.2591	0.0361	2.2599	1.5033
0.0688	76.0	228	2.2099	0.0349	2.2106	1.4868
0.0942	76.6667	230	1.8292	0.0190	1.8299	1.3527
0.0942	77.3333	232	1.4962	0.0331	1.4969	1.2235
0.0942	78.0	234	1.3329	0.0764	1.3336	1.1548
0.0942	78.6667	236	1.4241	0.0604	1.4248	1.1937
0.0942	79.3333	238	1.7210	0.0070	1.7217	1.3121
0.069	80.0	240	1.8527	0.0099	1.8534	1.3614
0.069	80.6667	242	1.6912	0.0163	1.6919	1.3007
0.069	81.3333	244	1.5813	0.0285	1.5820	1.2578
0.069	82.0	246	1.5497	0.0176	1.5504	1.2452
0.069	82.6667	248	1.6654	0.0276	1.6662	1.2908
0.0599	83.3333	250	1.6289	0.0167	1.6297	1.2766
0.0599	84.0	252	1.5533	0.0376	1.5541	1.2466
0.0599	84.6667	254	1.5454	0.0400	1.5462	1.2435
0.0599	85.3333	256	1.5764	0.0277	1.5771	1.2558
0.0599	86.0	258	1.5978	0.0233	1.5986	1.2643
0.0523	86.6667	260	1.5541	0.0269	1.5549	1.2470
0.0523	87.3333	262	1.5125	0.0371	1.5133	1.2301
0.0523	88.0	264	1.4808	0.0236	1.4816	1.2172
0.0523	88.6667	266	1.5303	0.0261	1.5310	1.2374
0.0523	89.3333	268	1.5621	0.0240	1.5630	1.2502
0.0658	90.0	270	1.6408	0.0075	1.6417	1.2813
0.0658	90.6667	272	1.6875	0.0074	1.6884	1.2994
0.0658	91.3333	274	1.6678	0.0067	1.6686	1.2918
0.0658	92.0	276	1.6405	0.0114	1.6414	1.2812
0.0658	92.6667	278	1.5920	0.0265	1.5928	1.2621
0.0493	93.3333	280	1.5526	0.0190	1.5534	1.2464
0.0493	94.0	282	1.4926	0.0157	1.4934	1.2220
0.0493	94.6667	284	1.4909	0.0157	1.4918	1.2214
0.0493	95.3333	286	1.4998	0.0131	1.5006	1.2250
0.0493	96.0	288	1.5467	0.0224	1.5475	1.2440
0.0602	96.6667	290	1.6004	0.0208	1.6012	1.2654
0.0602	97.3333	292	1.6359	0.0121	1.6367	1.2793
0.0602	98.0	294	1.6481	0.0144	1.6490	1.2841
0.0602	98.6667	296	1.6502	0.0136	1.6510	1.2849
0.0602	99.3333	298	1.6409	0.0222	1.6417	1.2813
0.0521	100.0	300	1.6350	0.0231	1.6358	1.2790

Framework versions

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