ASAP_FineTuningBERT_AugV5_k4_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: 1.1329
• Qwk: 0.3780
• Mse: 1.1330
• Rmse: 1.0644

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	10.7117	0.0053	10.7114	3.2728
No log	1.3333	4	9.5577	0.0	9.5575	3.0915
No log	2.0	6	7.9636	0.0	7.9634	2.8220
No log	2.6667	8	6.1491	0.0082	6.1489	2.4797
5.8547	3.3333	10	4.4595	0.0078	4.4595	2.1117
5.8547	4.0	12	3.2486	0.0	3.2487	1.8024
5.8547	4.6667	14	2.5375	0.0409	2.5378	1.5931
5.8547	5.3333	16	1.4979	0.0241	1.4980	1.2239
5.8547	6.0	18	1.2646	0.0115	1.2646	1.1245
2.101	6.6667	20	1.3153	0.0	1.3153	1.1469
2.101	7.3333	22	1.2655	0.0	1.2655	1.1249
2.101	8.0	24	1.3189	0.0	1.3189	1.1484
2.101	8.6667	26	1.5842	0.0	1.5842	1.2587
2.101	9.3333	28	1.4404	0.0	1.4405	1.2002
1.7618	10.0	30	1.2460	0.0	1.2461	1.1163
1.7618	10.6667	32	1.5953	0.0181	1.5953	1.2631
1.7618	11.3333	34	1.4416	0.0097	1.4416	1.2007
1.7618	12.0	36	1.2034	0.0	1.2035	1.0970
1.7618	12.6667	38	1.1086	0.0	1.1088	1.0530
1.6919	13.3333	40	1.4800	0.0247	1.4800	1.2166
1.6919	14.0	42	1.6453	0.0454	1.6453	1.2827
1.6919	14.6667	44	1.2997	0.0420	1.2998	1.1401
1.6919	15.3333	46	1.4696	0.0790	1.4695	1.2122
1.6919	16.0	48	1.1281	0.1725	1.1282	1.0621
1.5423	16.6667	50	1.0051	0.2676	1.0052	1.0026
1.5423	17.3333	52	2.0195	0.1542	2.0187	1.4208
1.5423	18.0	54	1.7553	0.1800	1.7546	1.3246
1.5423	18.6667	56	1.0008	0.2236	1.0009	1.0005
1.5423	19.3333	58	1.6340	0.1706	1.6334	1.2781
1.2664	20.0	60	1.5188	0.2014	1.5183	1.2322
1.2664	20.6667	62	0.9308	0.3463	0.9311	0.9649
1.2664	21.3333	64	1.9508	0.2470	1.9497	1.3963
1.2664	22.0	66	1.8380	0.2414	1.8371	1.3554
1.2664	22.6667	68	1.0053	0.3343	1.0057	1.0029
0.8963	23.3333	70	1.8924	0.2372	1.8916	1.3753
0.8963	24.0	72	1.6462	0.2494	1.6457	1.2829
0.8963	24.6667	74	0.9347	0.3449	0.9351	0.9670
0.8963	25.3333	76	1.6332	0.2458	1.6327	1.2778
0.8963	26.0	78	1.4823	0.2646	1.4820	1.2174
0.6293	26.6667	80	0.9280	0.3031	0.9284	0.9635
0.6293	27.3333	82	1.6647	0.2525	1.6641	1.2900
0.6293	28.0	84	1.6358	0.2464	1.6353	1.2788
0.6293	28.6667	86	1.0228	0.3032	1.0232	1.0115
0.6293	29.3333	88	1.8608	0.2288	1.8601	1.3638
0.4218	30.0	90	1.7701	0.2336	1.7695	1.3302
0.4218	30.6667	92	1.0591	0.3212	1.0595	1.0293
0.4218	31.3333	94	1.8084	0.2410	1.8078	1.3445
0.4218	32.0	96	1.6573	0.2456	1.6568	1.2872
0.4218	32.6667	98	1.0233	0.3282	1.0237	1.0118
0.3432	33.3333	100	1.6590	0.2471	1.6585	1.2878
0.3432	34.0	102	1.5391	0.2528	1.5387	1.2404
0.3432	34.6667	104	1.0098	0.3488	1.0101	1.0050
0.3432	35.3333	106	1.5953	0.2553	1.5947	1.2628
0.3432	36.0	108	1.4915	0.2603	1.4912	1.2211
0.2485	36.6667	110	1.0365	0.3681	1.0368	1.0183
0.2485	37.3333	112	1.7052	0.2609	1.7046	1.3056
0.2485	38.0	114	1.6595	0.2803	1.6590	1.2880
0.2485	38.6667	116	1.1268	0.3639	1.1270	1.0616
0.2485	39.3333	118	1.6399	0.2838	1.6395	1.2804
0.2295	40.0	120	1.4232	0.3015	1.4230	1.1929
0.2295	40.6667	122	1.0620	0.3889	1.0623	1.0307
0.2295	41.3333	124	1.6320	0.3030	1.6315	1.2773
0.2295	42.0	126	1.6095	0.3091	1.6090	1.2685
0.2295	42.6667	128	1.1056	0.3977	1.1057	1.0515
0.1805	43.3333	130	1.4969	0.3105	1.4965	1.2233
0.1805	44.0	132	1.3641	0.3228	1.3637	1.1678
0.1805	44.6667	134	1.0115	0.4215	1.0117	1.0058
0.1805	45.3333	136	1.3866	0.3275	1.3862	1.1774
0.1805	46.0	138	1.3714	0.3400	1.3710	1.1709
0.1606	46.6667	140	1.0935	0.4078	1.0936	1.0458
0.1606	47.3333	142	1.2099	0.3682	1.2097	1.0999
0.1606	48.0	144	1.7931	0.2690	1.7924	1.3388
0.1606	48.6667	146	1.3238	0.3396	1.3235	1.1504
0.1606	49.3333	148	1.1842	0.3689	1.1842	1.0882
0.1642	50.0	150	1.3593	0.3325	1.3590	1.1658
0.1642	50.6667	152	1.1897	0.3688	1.1896	1.0907
0.1642	51.3333	154	1.3304	0.3454	1.3300	1.1533
0.1642	52.0	156	1.1747	0.3755	1.1746	1.0838
0.1642	52.6667	158	1.3170	0.3438	1.3166	1.1474
0.1163	53.3333	160	1.0703	0.4184	1.0704	1.0346
0.1163	54.0	162	1.2428	0.3762	1.2426	1.1147
0.1163	54.6667	164	1.3523	0.3376	1.3520	1.1627
0.1163	55.3333	166	1.2638	0.3707	1.2636	1.1241
0.1163	56.0	168	1.3318	0.3516	1.3315	1.1539
0.1191	56.6667	170	1.1825	0.3837	1.1824	1.0874
0.1191	57.3333	172	1.2999	0.3538	1.2997	1.1401
0.1191	58.0	174	1.0629	0.4264	1.0630	1.0310
0.1191	58.6667	176	1.2063	0.3884	1.2064	1.0984
0.1191	59.3333	178	1.6948	0.2946	1.6945	1.3017
0.1279	60.0	180	1.4071	0.3425	1.4071	1.1862
0.1279	60.6667	182	1.1029	0.3961	1.1032	1.0503
0.1279	61.3333	184	1.1897	0.3897	1.1899	1.0908
0.1279	62.0	186	1.5816	0.2959	1.5813	1.2575
0.1279	62.6667	188	1.3318	0.3300	1.3316	1.1540
0.1118	63.3333	190	1.0335	0.4199	1.0336	1.0167
0.1118	64.0	192	1.1341	0.3858	1.1341	1.0649
0.1118	64.6667	194	1.4467	0.3076	1.4464	1.2027
0.1118	65.3333	196	1.2405	0.3788	1.2403	1.1137
0.1118	66.0	198	1.0421	0.4018	1.0423	1.0209
0.1188	66.6667	200	1.1169	0.3852	1.1169	1.0569
0.1188	67.3333	202	1.3896	0.3243	1.3893	1.1787
0.1188	68.0	204	1.2522	0.3731	1.2521	1.1190
0.1188	68.6667	206	1.0825	0.3899	1.0826	1.0405
0.1188	69.3333	208	1.1421	0.3891	1.1422	1.0687
0.0979	70.0	210	1.3888	0.3175	1.3886	1.1784
0.0979	70.6667	212	1.2508	0.3742	1.2507	1.1184
0.0979	71.3333	214	1.0699	0.3997	1.0701	1.0344
0.0979	72.0	216	1.1400	0.3863	1.1400	1.0677
0.0979	72.6667	218	1.1723	0.3830	1.1723	1.0827
0.0871	73.3333	220	1.1686	0.3880	1.1686	1.0810
0.0871	74.0	222	1.2582	0.3650	1.2580	1.1216
0.0871	74.6667	224	1.1550	0.3862	1.1550	1.0747
0.0871	75.3333	226	1.0538	0.4068	1.0539	1.0266
0.0871	76.0	228	1.1532	0.3921	1.1532	1.0739
0.0822	76.6667	230	1.3724	0.3266	1.3723	1.1714
0.0822	77.3333	232	1.2698	0.3728	1.2698	1.1268
0.0822	78.0	234	1.0713	0.4095	1.0716	1.0352
0.0822	78.6667	236	1.0481	0.4084	1.0484	1.0239
0.0822	79.3333	238	1.1305	0.4081	1.1306	1.0633
0.1003	80.0	240	1.3567	0.3385	1.3565	1.1647
0.1003	80.6667	242	1.3199	0.3412	1.3198	1.1488
0.1003	81.3333	244	1.1253	0.4004	1.1253	1.0608
0.1003	82.0	246	1.0874	0.4069	1.0874	1.0428
0.1003	82.6667	248	1.1779	0.3768	1.1778	1.0853
0.0767	83.3333	250	1.1647	0.3747	1.1646	1.0792
0.0767	84.0	252	1.1000	0.3960	1.1000	1.0488
0.0767	84.6667	254	1.1100	0.4024	1.1100	1.0536
0.0767	85.3333	256	1.1787	0.3962	1.1787	1.0857
0.0767	86.0	258	1.1919	0.3888	1.1919	1.0918
0.0657	86.6667	260	1.1310	0.4007	1.1311	1.0635
0.0657	87.3333	262	1.1526	0.3930	1.1527	1.0736
0.0657	88.0	264	1.1796	0.3927	1.1796	1.0861
0.0657	88.6667	266	1.1828	0.3866	1.1828	1.0876
0.0657	89.3333	268	1.1727	0.3900	1.1728	1.0830
0.0643	90.0	270	1.2086	0.3867	1.2086	1.0994
0.0643	90.6667	272	1.1789	0.3895	1.1790	1.0858
0.0643	91.3333	274	1.1231	0.3910	1.1232	1.0598
0.0643	92.0	276	1.0864	0.4037	1.0865	1.0424
0.0643	92.6667	278	1.0870	0.3943	1.0871	1.0426
0.0541	93.3333	280	1.1382	0.3754	1.1383	1.0669
0.0541	94.0	282	1.1724	0.3614	1.1724	1.0828
0.0541	94.6667	284	1.1468	0.3647	1.1467	1.0709
0.0541	95.3333	286	1.0903	0.4016	1.0903	1.0442
0.0541	96.0	288	1.0445	0.4210	1.0446	1.0221
0.0624	96.6667	290	1.0397	0.4272	1.0398	1.0197
0.0624	97.3333	292	1.0571	0.4060	1.0572	1.0282
0.0624	98.0	294	1.0860	0.4004	1.0861	1.0421
0.0624	98.6667	296	1.1159	0.3853	1.1160	1.0564
0.0624	99.3333	298	1.1293	0.3783	1.1294	1.0627
0.0576	100.0	300	1.1329	0.3780	1.1330	1.0644

Framework versions

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