ASAP_FineTuningBERT_AugV6_k2_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: 1.1448
• Qwk: 0.4410
• Mse: 1.1439
• Rmse: 1.0695

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	1.0	2	10.7158	-0.0077	10.7133	3.2731
No log	2.0	4	8.3122	0.0	8.3103	2.8828
No log	3.0	6	6.5809	0.0	6.5791	2.5650
No log	4.0	8	5.2714	0.0219	5.2700	2.2956
6.3556	5.0	10	4.0074	0.0040	4.0064	2.0016
6.3556	6.0	12	3.0440	0.0	3.0432	1.7445
6.3556	7.0	14	2.4480	-0.0037	2.4475	1.5644
6.3556	8.0	16	1.8615	0.0669	1.8613	1.3643
6.3556	9.0	18	1.5608	0.0106	1.5608	1.2493
2.4488	10.0	20	1.2514	0.0106	1.2515	1.1187
2.4488	11.0	22	1.1488	0.0106	1.1490	1.0719
2.4488	12.0	24	1.2662	0.0106	1.2664	1.1253
2.4488	13.0	26	1.1856	0.0315	1.1857	1.0889
2.4488	14.0	28	0.9949	0.0521	0.9950	0.9975
1.783	15.0	30	1.0346	0.1683	1.0346	1.0172
1.783	16.0	32	1.1401	0.1537	1.1401	1.0678
1.783	17.0	34	0.8525	0.3462	0.8526	0.9233
1.783	18.0	36	0.9109	0.3087	0.9109	0.9544
1.783	19.0	38	0.7036	0.4534	0.7036	0.8388
1.2744	20.0	40	0.8109	0.3039	0.8110	0.9006
1.2744	21.0	42	0.6317	0.4528	0.6318	0.7949
1.2744	22.0	44	0.8021	0.3146	0.8023	0.8957
1.2744	23.0	46	0.6614	0.4031	0.6615	0.8133
1.2744	24.0	48	0.8952	0.2442	0.8954	0.9463
0.6914	25.0	50	0.6814	0.3810	0.6814	0.8254
0.6914	26.0	52	0.8218	0.3288	0.8218	0.9065
0.6914	27.0	54	0.7396	0.3786	0.7395	0.8599
0.6914	28.0	56	0.6287	0.4553	0.6286	0.7928
0.6914	29.0	58	0.9749	0.2446	0.9749	0.9874
0.474	30.0	60	0.8070	0.3678	0.8069	0.8983
0.474	31.0	62	0.5358	0.5600	0.5356	0.7318
0.474	32.0	64	0.8668	0.3751	0.8666	0.9309
0.474	33.0	66	1.2490	0.1574	1.2491	1.1176
0.474	34.0	68	0.7519	0.4896	0.7516	0.8669
0.4074	35.0	70	0.7474	0.5015	0.7471	0.8643
0.4074	36.0	72	1.0359	0.2944	1.0358	1.0177
0.4074	37.0	74	0.7322	0.5270	0.7319	0.8555
0.4074	38.0	76	0.8105	0.4989	0.8102	0.9001
0.4074	39.0	78	1.1253	0.2595	1.1252	1.0607
0.2859	40.0	80	0.8086	0.5079	0.8083	0.8990
0.2859	41.0	82	0.8835	0.4552	0.8832	0.9398
0.2859	42.0	84	1.0433	0.3642	1.0431	1.0213
0.2859	43.0	86	0.9794	0.4176	0.9790	0.9895
0.2859	44.0	88	1.1257	0.3222	1.1254	1.0609
0.2135	45.0	90	1.0142	0.3960	1.0138	1.0069
0.2135	46.0	92	1.1155	0.3586	1.1152	1.0560
0.2135	47.0	94	1.0376	0.4093	1.0370	1.0183
0.2135	48.0	96	1.3530	0.2487	1.3527	1.1630
0.2135	49.0	98	1.3032	0.2987	1.3028	1.1414
0.195	50.0	100	1.0014	0.4474	1.0007	1.0003
0.195	51.0	102	1.1582	0.3548	1.1576	1.0759
0.195	52.0	104	1.1044	0.3964	1.1037	1.0506
0.195	53.0	106	0.9584	0.4740	0.9577	0.9786
0.195	54.0	108	1.1789	0.3501	1.1784	1.0855
0.1629	55.0	110	1.1975	0.3583	1.1969	1.0940
0.1629	56.0	112	1.1943	0.3572	1.1937	1.0926
0.1629	57.0	114	1.0032	0.4606	1.0025	1.0012
0.1629	58.0	116	1.0562	0.4242	1.0555	1.0274
0.1629	59.0	118	1.3335	0.3011	1.3329	1.1545
0.1505	60.0	120	1.2705	0.3531	1.2697	1.1268
0.1505	61.0	122	1.3065	0.3599	1.3057	1.1427
0.1505	62.0	124	1.4995	0.2422	1.4990	1.2243
0.1505	63.0	126	1.4697	0.2475	1.4692	1.2121
0.1505	64.0	128	1.1872	0.3841	1.1864	1.0892
0.1517	65.0	130	1.0728	0.4328	1.0720	1.0354
0.1517	66.0	132	1.1772	0.3791	1.1765	1.0847
0.1517	67.0	134	1.2172	0.3851	1.2165	1.1029
0.1517	68.0	136	1.1582	0.4303	1.1574	1.0758
0.1517	69.0	138	1.1800	0.4207	1.1792	1.0859
0.1196	70.0	140	1.1957	0.4141	1.1949	1.0931
0.1196	71.0	142	1.1450	0.4298	1.1442	1.0697
0.1196	72.0	144	1.2040	0.4223	1.2031	1.0969
0.1196	73.0	146	1.2350	0.3933	1.2342	1.1109
0.1196	74.0	148	1.1945	0.4070	1.1936	1.0925
0.1021	75.0	150	1.1052	0.4401	1.1043	1.0508
0.1021	76.0	152	1.1365	0.4121	1.1356	1.0657
0.1021	77.0	154	1.2479	0.3307	1.2472	1.1168
0.1021	78.0	156	1.3010	0.3690	1.3002	1.1403
0.1021	79.0	158	1.3130	0.4064	1.3120	1.1454
0.1123	80.0	160	1.3795	0.4023	1.3785	1.1741
0.1123	81.0	162	1.4750	0.3605	1.4742	1.2142
0.1123	82.0	164	1.4007	0.3528	1.4000	1.1832
0.1123	83.0	166	1.2203	0.3888	1.2195	1.1043
0.1123	84.0	168	1.0353	0.4809	1.0344	1.0170
0.1066	85.0	170	0.9608	0.5082	0.9599	0.9797
0.1066	86.0	172	0.9956	0.4931	0.9948	0.9974
0.1066	87.0	174	1.1219	0.4210	1.1210	1.0588
0.1066	88.0	176	1.2118	0.3898	1.2110	1.1004
0.1066	89.0	178	1.2135	0.4110	1.2126	1.1012
0.0999	90.0	180	1.1746	0.4321	1.1736	1.0834
0.0999	91.0	182	1.1774	0.4286	1.1764	1.0846
0.0999	92.0	184	1.1884	0.4194	1.1875	1.0897
0.0999	93.0	186	1.2155	0.4141	1.2146	1.1021
0.0999	94.0	188	1.2217	0.4089	1.2208	1.1049
0.0873	95.0	190	1.2050	0.4090	1.2040	1.0973
0.0873	96.0	192	1.1722	0.4326	1.1712	1.0822
0.0873	97.0	194	1.1553	0.4353	1.1544	1.0744
0.0873	98.0	196	1.1463	0.4408	1.1454	1.0702
0.0873	99.0	198	1.1422	0.4426	1.1412	1.0683
0.0817	100.0	200	1.1448	0.4410	1.1439	1.0695

Framework versions

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