ASAP_FineTuningBERT_AugV6_k3_task1_organization

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: 0.8757
• Qwk: 0.2822
• Mse: 0.8757
• Rmse: 0.9358

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0909	2	13.3259	0.0	13.3259	3.6505
No log	0.1818	4	10.8135	0.0054	10.8135	3.2884
No log	0.2727	6	9.2552	0.0	9.2552	3.0422
No log	0.3636	8	7.2952	0.0	7.2952	2.7010
7.0477	0.4545	10	5.8136	0.0503	5.8136	2.4111
7.0477	0.5455	12	4.5663	0.0115	4.5663	2.1369
7.0477	0.6364	14	3.4267	0.0077	3.4267	1.8511
7.0477	0.7273	16	2.3813	0.0766	2.3813	1.5431
7.0477	0.8182	18	2.3625	0.0091	2.3625	1.5370
2.41	0.9091	20	1.7764	0.0316	1.7764	1.3328
2.41	1.0	22	1.4621	0.0316	1.4621	1.2092
2.41	1.0909	24	1.6891	0.0316	1.6891	1.2997
2.41	1.1818	26	1.6241	0.0316	1.6241	1.2744
2.41	1.2727	28	1.5799	0.0316	1.5799	1.2569
1.6303	1.3636	30	1.4306	0.0212	1.4306	1.1961
1.6303	1.4545	32	1.5917	0.0240	1.5917	1.2616
1.6303	1.5455	34	1.9057	0.0791	1.9057	1.3805
1.6303	1.6364	36	1.6437	0.0703	1.6437	1.2821
1.6303	1.7273	38	1.1827	0.0258	1.1827	1.0875
1.7052	1.8182	40	1.2469	0.0212	1.2469	1.1166
1.7052	1.9091	42	1.8504	0.0746	1.8504	1.3603
1.7052	2.0	44	2.3254	0.1035	2.3254	1.5249
1.7052	2.0909	46	2.1491	0.1119	2.1491	1.4660
1.7052	2.1818	48	1.7988	0.0740	1.7988	1.3412
1.7104	2.2727	50	1.3834	0.0409	1.3834	1.1762
1.7104	2.3636	52	1.3625	0.0527	1.3625	1.1673
1.7104	2.4545	54	1.4800	0.0678	1.4800	1.2166
1.7104	2.5455	56	2.2820	0.1010	2.2820	1.5106
1.7104	2.6364	58	2.0384	0.1188	2.0384	1.4277
1.5739	2.7273	60	1.0875	0.1640	1.0875	1.0428
1.5739	2.8182	62	0.9234	0.2485	0.9234	0.9609
1.5739	2.9091	64	1.3960	0.0679	1.3960	1.1815
1.5739	3.0	66	2.4707	0.0703	2.4707	1.5718
1.5739	3.0909	68	2.0553	0.0646	2.0553	1.4336
1.5759	3.1818	70	1.0688	0.2205	1.0688	1.0338
1.5759	3.2727	72	1.2113	0.2243	1.2113	1.1006
1.5759	3.3636	74	1.3066	0.2067	1.3066	1.1430
1.5759	3.4545	76	1.2178	0.2070	1.2178	1.1035
1.5759	3.5455	78	0.9197	0.2527	0.9197	0.9590
1.1454	3.6364	80	0.7959	0.2597	0.7959	0.8921
1.1454	3.7273	82	1.1511	0.2361	1.1511	1.0729
1.1454	3.8182	84	0.8580	0.2142	0.8580	0.9263
1.1454	3.9091	86	0.8239	0.2540	0.8239	0.9077
1.1454	4.0	88	1.3020	0.2062	1.3020	1.1410
0.8467	4.0909	90	1.0191	0.2431	1.0191	1.0095
0.8467	4.1818	92	0.7843	0.3488	0.7843	0.8856
0.8467	4.2727	94	0.8601	0.3018	0.8601	0.9274
0.8467	4.3636	96	1.4558	0.1750	1.4558	1.2066
0.8467	4.4545	98	0.9107	0.3147	0.9107	0.9543
0.8554	4.5455	100	0.7619	0.3747	0.7619	0.8729
0.8554	4.6364	102	0.7073	0.3651	0.7073	0.8410
0.8554	4.7273	104	1.1630	0.2601	1.1630	1.0784
0.8554	4.8182	106	1.3148	0.2188	1.3148	1.1467
0.8554	4.9091	108	0.8109	0.3662	0.8109	0.9005
0.6414	5.0	110	0.8826	0.3403	0.8826	0.9394
0.6414	5.0909	112	0.7807	0.3855	0.7807	0.8836
0.6414	5.1818	114	1.1318	0.2639	1.1318	1.0639
0.6414	5.2727	116	1.4017	0.2104	1.4017	1.1839
0.6414	5.3636	118	0.8549	0.3559	0.8549	0.9246
0.6403	5.4545	120	0.8716	0.3244	0.8716	0.9336
0.6403	5.5455	122	0.8638	0.3532	0.8638	0.9294
0.6403	5.6364	124	1.2091	0.2646	1.2091	1.0996
0.6403	5.7273	126	0.9884	0.3270	0.9884	0.9942
0.6403	5.8182	128	0.8172	0.3838	0.8172	0.9040
0.4962	5.9091	130	0.8535	0.3721	0.8535	0.9238
0.4962	6.0	132	0.8208	0.3460	0.8208	0.9060
0.4962	6.0909	134	0.9276	0.3035	0.9276	0.9631
0.4962	6.1818	136	0.8273	0.3463	0.8273	0.9096
0.4962	6.2727	138	0.8626	0.3300	0.8626	0.9287
0.353	6.3636	140	0.9416	0.3163	0.9416	0.9704
0.353	6.4545	142	0.9335	0.3272	0.9335	0.9662
0.353	6.5455	144	0.9798	0.3144	0.9798	0.9899
0.353	6.6364	146	0.9383	0.3156	0.9383	0.9687
0.353	6.7273	148	0.9299	0.3303	0.9299	0.9643
0.3396	6.8182	150	0.8417	0.3495	0.8417	0.9174
0.3396	6.9091	152	0.8616	0.3206	0.8616	0.9282
0.3396	7.0	154	1.0498	0.2967	1.0498	1.0246
0.3396	7.0909	156	0.8648	0.3743	0.8648	0.9300
0.3396	7.1818	158	0.9069	0.3995	0.9069	0.9523
0.2668	7.2727	160	1.1075	0.3278	1.1075	1.0524
0.2668	7.3636	162	1.0852	0.3459	1.0852	1.0417
0.2668	7.4545	164	1.0086	0.3201	1.0086	1.0043
0.2668	7.5455	166	1.0664	0.2964	1.0664	1.0327
0.2668	7.6364	168	0.9085	0.3057	0.9085	0.9531
0.2297	7.7273	170	0.8958	0.3051	0.8958	0.9465
0.2297	7.8182	172	1.0026	0.2951	1.0026	1.0013
0.2297	7.9091	174	0.9612	0.3091	0.9612	0.9804
0.2297	8.0	176	1.0044	0.3177	1.0044	1.0022
0.2297	8.0909	178	1.1047	0.3032	1.1047	1.0510
0.2269	8.1818	180	1.0171	0.3240	1.0171	1.0085
0.2269	8.2727	182	0.9894	0.3335	0.9894	0.9947
0.2269	8.3636	184	1.0406	0.3203	1.0406	1.0201
0.2269	8.4545	186	0.9139	0.3571	0.9139	0.9560
0.2269	8.5455	188	0.9030	0.3634	0.9030	0.9503
0.1885	8.6364	190	1.0094	0.3183	1.0094	1.0047
0.1885	8.7273	192	0.9486	0.3190	0.9486	0.9740
0.1885	8.8182	194	0.9653	0.3210	0.9653	0.9825
0.1885	8.9091	196	0.9803	0.3110	0.9803	0.9901
0.1885	9.0	198	0.9456	0.3070	0.9456	0.9724
0.2024	9.0909	200	0.9148	0.3231	0.9148	0.9565
0.2024	9.1818	202	0.9464	0.3295	0.9464	0.9728
0.2024	9.2727	204	0.8621	0.3230	0.8621	0.9285
0.2024	9.3636	206	0.8716	0.3489	0.8716	0.9336
0.2024	9.4545	208	0.9337	0.3413	0.9337	0.9663
0.1771	9.5455	210	0.9605	0.3446	0.9605	0.9800
0.1771	9.6364	212	0.9265	0.3568	0.9265	0.9625
0.1771	9.7273	214	0.9237	0.3501	0.9237	0.9611
0.1771	9.8182	216	0.8794	0.3463	0.8794	0.9377
0.1771	9.9091	218	0.8513	0.3601	0.8513	0.9227
0.1598	10.0	220	0.8835	0.3540	0.8835	0.9400
0.1598	10.0909	222	0.8197	0.3793	0.8197	0.9053
0.1598	10.1818	224	0.8305	0.3708	0.8305	0.9113
0.1598	10.2727	226	0.8939	0.3409	0.8939	0.9455
0.1598	10.3636	228	0.8948	0.3521	0.8948	0.9459
0.1599	10.4545	230	0.9118	0.3537	0.9118	0.9549
0.1599	10.5455	232	0.9225	0.3226	0.9225	0.9604
0.1599	10.6364	234	0.8724	0.3592	0.8724	0.9340
0.1599	10.7273	236	0.8649	0.3407	0.8649	0.9300
0.1599	10.8182	238	0.8790	0.3131	0.8790	0.9375
0.1268	10.9091	240	0.9282	0.3172	0.9282	0.9635
0.1268	11.0	242	0.9612	0.2866	0.9612	0.9804
0.1268	11.0909	244	0.9436	0.2863	0.9436	0.9714
0.1268	11.1818	246	0.9482	0.2710	0.9482	0.9738
0.1268	11.2727	248	0.8756	0.2694	0.8756	0.9357
0.1208	11.3636	250	0.9211	0.2930	0.9211	0.9597
0.1208	11.4545	252	0.9081	0.3017	0.9081	0.9530
0.1208	11.5455	254	0.9742	0.3124	0.9742	0.9870
0.1208	11.6364	256	1.0219	0.3136	1.0219	1.0109
0.1208	11.7273	258	0.9681	0.3070	0.9681	0.9839
0.1235	11.8182	260	0.9311	0.3072	0.9311	0.9649
0.1235	11.9091	262	0.9819	0.3088	0.9819	0.9909
0.1235	12.0	264	0.9503	0.2907	0.9503	0.9748
0.1235	12.0909	266	0.9616	0.2928	0.9616	0.9806
0.1235	12.1818	268	0.9558	0.2839	0.9558	0.9776
0.1101	12.2727	270	0.9577	0.3004	0.9577	0.9786
0.1101	12.3636	272	0.8998	0.2862	0.8998	0.9486
0.1101	12.4545	274	0.8354	0.3323	0.8354	0.9140
0.1101	12.5455	276	0.8304	0.3353	0.8304	0.9113
0.1101	12.6364	278	0.9107	0.3065	0.9107	0.9543
0.1071	12.7273	280	0.8985	0.3372	0.8985	0.9479
0.1071	12.8182	282	0.9397	0.3494	0.9397	0.9694
0.1071	12.9091	284	0.9306	0.3335	0.9306	0.9647
0.1071	13.0	286	0.8970	0.3255	0.8970	0.9471
0.1071	13.0909	288	0.9004	0.3037	0.9004	0.9489
0.1092	13.1818	290	0.9897	0.2734	0.9897	0.9948
0.1092	13.2727	292	0.9215	0.2717	0.9215	0.9600
0.1092	13.3636	294	0.8638	0.2902	0.8638	0.9294
0.1092	13.4545	296	0.8976	0.2636	0.8976	0.9474
0.1092	13.5455	298	0.9769	0.2492	0.9769	0.9884
0.1078	13.6364	300	0.9627	0.2829	0.9627	0.9812
0.1078	13.7273	302	0.9899	0.3149	0.9899	0.9949
0.1078	13.8182	304	0.9613	0.3200	0.9613	0.9804
0.1078	13.9091	306	0.9188	0.3153	0.9188	0.9585
0.1078	14.0	308	0.8799	0.3048	0.8799	0.9380
0.1005	14.0909	310	0.8675	0.3058	0.8675	0.9314
0.1005	14.1818	312	0.9397	0.3341	0.9397	0.9694
0.1005	14.2727	314	0.9507	0.3089	0.9507	0.9750
0.1005	14.3636	316	0.9471	0.3099	0.9471	0.9732
0.1005	14.4545	318	0.9302	0.2837	0.9302	0.9645
0.0868	14.5455	320	0.9450	0.2759	0.9450	0.9721
0.0868	14.6364	322	0.9156	0.2785	0.9156	0.9568
0.0868	14.7273	324	0.8630	0.3120	0.8630	0.9290
0.0868	14.8182	326	0.8407	0.3100	0.8407	0.9169
0.0868	14.9091	328	0.8825	0.2808	0.8825	0.9394
0.0916	15.0	330	0.9140	0.2941	0.9140	0.9560
0.0916	15.0909	332	0.9482	0.3132	0.9482	0.9738
0.0916	15.1818	334	0.9741	0.3104	0.9741	0.9870
0.0916	15.2727	336	0.9694	0.2891	0.9694	0.9846
0.0916	15.3636	338	0.8984	0.2966	0.8984	0.9478
0.0888	15.4545	340	0.8775	0.2916	0.8775	0.9367
0.0888	15.5455	342	0.8643	0.2944	0.8643	0.9297
0.0888	15.6364	344	0.8522	0.2998	0.8522	0.9232
0.0888	15.7273	346	0.8795	0.2968	0.8795	0.9378
0.0888	15.8182	348	0.8755	0.3009	0.8755	0.9357
0.0751	15.9091	350	0.8669	0.3337	0.8669	0.9311
0.0751	16.0	352	0.9007	0.3317	0.9007	0.9491
0.0751	16.0909	354	0.8990	0.2856	0.8990	0.9482
0.0751	16.1818	356	0.9510	0.3053	0.9510	0.9752
0.0751	16.2727	358	0.9069	0.3114	0.9069	0.9523
0.0876	16.3636	360	0.8583	0.3177	0.8583	0.9265
0.0876	16.4545	362	0.8679	0.3006	0.8679	0.9316
0.0876	16.5455	364	0.9136	0.3070	0.9136	0.9558
0.0876	16.6364	366	0.8951	0.3037	0.8951	0.9461
0.0876	16.7273	368	0.8925	0.2979	0.8925	0.9447
0.0667	16.8182	370	0.9234	0.3031	0.9234	0.9609
0.0667	16.9091	372	0.9146	0.2875	0.9146	0.9563
0.0667	17.0	374	0.8927	0.2970	0.8927	0.9448
0.0667	17.0909	376	0.8946	0.2870	0.8946	0.9458
0.0667	17.1818	378	0.8754	0.2903	0.8754	0.9356
0.0911	17.2727	380	0.9084	0.2895	0.9084	0.9531
0.0911	17.3636	382	0.9020	0.2912	0.9020	0.9497
0.0911	17.4545	384	0.8957	0.2936	0.8957	0.9464
0.0911	17.5455	386	0.8807	0.2979	0.8807	0.9385
0.0911	17.6364	388	0.8802	0.2733	0.8802	0.9382
0.0727	17.7273	390	0.8506	0.2674	0.8506	0.9223
0.0727	17.8182	392	0.8425	0.2835	0.8425	0.9179
0.0727	17.9091	394	0.8516	0.2848	0.8516	0.9228
0.0727	18.0	396	0.8642	0.2991	0.8642	0.9296
0.0727	18.0909	398	0.8557	0.3015	0.8557	0.9250
0.071	18.1818	400	0.8443	0.2948	0.8443	0.9189
0.071	18.2727	402	0.8456	0.3216	0.8456	0.9196
0.071	18.3636	404	0.8384	0.3170	0.8384	0.9156
0.071	18.4545	406	0.8700	0.3307	0.8700	0.9327
0.071	18.5455	408	0.9326	0.3099	0.9326	0.9657
0.0679	18.6364	410	0.9565	0.3063	0.9565	0.9780
0.0679	18.7273	412	0.9050	0.3165	0.9050	0.9513
0.0679	18.8182	414	0.8994	0.3279	0.8994	0.9484
0.0679	18.9091	416	0.8956	0.3174	0.8956	0.9464
0.0679	19.0	418	0.9188	0.2973	0.9188	0.9585
0.0758	19.0909	420	0.9445	0.3071	0.9445	0.9718
0.0758	19.1818	422	0.8980	0.2865	0.8980	0.9476
0.0758	19.2727	424	0.8662	0.3231	0.8662	0.9307
0.0758	19.3636	426	0.8828	0.3164	0.8828	0.9396
0.0758	19.4545	428	0.8865	0.3151	0.8865	0.9415
0.0691	19.5455	430	0.9365	0.2760	0.9365	0.9677
0.0691	19.6364	432	0.9514	0.2803	0.9514	0.9754
0.0691	19.7273	434	0.9178	0.2950	0.9178	0.9580
0.0691	19.8182	436	0.9124	0.3195	0.9124	0.9552
0.0691	19.9091	438	0.8956	0.3194	0.8956	0.9464
0.0765	20.0	440	0.8861	0.3046	0.8861	0.9413
0.0765	20.0909	442	0.8814	0.2913	0.8814	0.9388
0.0765	20.1818	444	0.8743	0.2969	0.8743	0.9350
0.0765	20.2727	446	0.8487	0.2915	0.8487	0.9212
0.0765	20.3636	448	0.8291	0.2938	0.8291	0.9106
0.0617	20.4545	450	0.8415	0.2800	0.8415	0.9173
0.0617	20.5455	452	0.8889	0.2766	0.8889	0.9428
0.0617	20.6364	454	0.9087	0.2817	0.9087	0.9532
0.0617	20.7273	456	0.8943	0.2933	0.8943	0.9457
0.0617	20.8182	458	0.8918	0.3131	0.8918	0.9443
0.0642	20.9091	460	0.8890	0.3124	0.8890	0.9429
0.0642	21.0	462	0.8989	0.3000	0.8989	0.9481
0.0642	21.0909	464	0.9064	0.2972	0.9064	0.9520
0.0642	21.1818	466	0.8734	0.2939	0.8734	0.9346
0.0642	21.2727	468	0.8555	0.2985	0.8555	0.9249
0.0615	21.3636	470	0.8608	0.2985	0.8608	0.9278
0.0615	21.4545	472	0.8681	0.2919	0.8681	0.9317
0.0615	21.5455	474	0.8856	0.2968	0.8856	0.9411
0.0615	21.6364	476	0.9006	0.2977	0.9006	0.9490
0.0615	21.7273	478	0.9237	0.2790	0.9237	0.9611
0.0582	21.8182	480	0.9230	0.2969	0.9230	0.9608
0.0582	21.9091	482	0.9162	0.3022	0.9162	0.9572
0.0582	22.0	484	0.9101	0.3041	0.9101	0.9540
0.0582	22.0909	486	0.9089	0.2772	0.9089	0.9534
0.0582	22.1818	488	0.8948	0.2753	0.8948	0.9459
0.0558	22.2727	490	0.8750	0.2879	0.8750	0.9354
0.0558	22.3636	492	0.8660	0.2953	0.8660	0.9306
0.0558	22.4545	494	0.8705	0.2932	0.8705	0.9330
0.0558	22.5455	496	0.8783	0.2859	0.8783	0.9372
0.0558	22.6364	498	0.8930	0.2945	0.8930	0.9450
0.0595	22.7273	500	0.8942	0.2840	0.8942	0.9456
0.0595	22.8182	502	0.8847	0.3149	0.8847	0.9406
0.0595	22.9091	504	0.8827	0.3050	0.8827	0.9395
0.0595	23.0	506	0.8806	0.3122	0.8806	0.9384
0.0595	23.0909	508	0.8780	0.3058	0.8780	0.9370
0.0581	23.1818	510	0.8783	0.3130	0.8783	0.9372
0.0581	23.2727	512	0.8812	0.2952	0.8812	0.9387
0.0581	23.3636	514	0.8952	0.2869	0.8952	0.9462
0.0581	23.4545	516	0.8997	0.2897	0.8997	0.9485
0.0581	23.5455	518	0.8884	0.2855	0.8884	0.9425
0.0639	23.6364	520	0.8813	0.2883	0.8813	0.9388
0.0639	23.7273	522	0.8744	0.3087	0.8744	0.9351
0.0639	23.8182	524	0.8741	0.3030	0.8741	0.9349
0.0639	23.9091	526	0.8706	0.3082	0.8706	0.9330
0.0639	24.0	528	0.8697	0.3042	0.8697	0.9326
0.0555	24.0909	530	0.8709	0.2866	0.8709	0.9332
0.0555	24.1818	532	0.8736	0.2879	0.8736	0.9347
0.0555	24.2727	534	0.8753	0.2895	0.8753	0.9356
0.0555	24.3636	536	0.8809	0.2887	0.8809	0.9386
0.0555	24.4545	538	0.8842	0.2984	0.8842	0.9403
0.0495	24.5455	540	0.8835	0.2887	0.8835	0.9399
0.0495	24.6364	542	0.8811	0.2842	0.8811	0.9387
0.0495	24.7273	544	0.8784	0.2826	0.8784	0.9373
0.0495	24.8182	546	0.8768	0.2822	0.8768	0.9364
0.0495	24.9091	548	0.8760	0.2822	0.8760	0.9359
0.0512	25.0	550	0.8757	0.2822	0.8757	0.9358

Framework versions

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