ASAP_FineTuningBERT_AugV5_k2_task1_organization_fold0

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: 2.5672
• Qwk: 0.1569
• Mse: 2.5672
• Rmse: 1.6023

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	8.9837	0.0	8.9837	2.9973
No log	2.0	4	7.5886	0.0	7.5886	2.7547
No log	3.0	6	6.7933	0.0	6.7933	2.6064
No log	4.0	8	5.9019	0.0334	5.9019	2.4294
4.9726	5.0	10	5.0055	0.0115	5.0055	2.2373
4.9726	6.0	12	4.2886	0.0039	4.2886	2.0709
4.9726	7.0	14	3.4374	0.0	3.4374	1.8540
4.9726	8.0	16	2.7480	0.0	2.7480	1.6577
4.9726	9.0	18	2.1294	0.0689	2.1294	1.4592
2.3566	10.0	20	1.9136	0.0664	1.9136	1.3833
2.3566	11.0	22	1.6575	0.0316	1.6575	1.2875
2.3566	12.0	24	1.5791	0.0316	1.5791	1.2566
2.3566	13.0	26	1.5508	0.0316	1.5508	1.2453
2.3566	14.0	28	2.2890	0.1589	2.2890	1.5129
1.7933	15.0	30	2.1373	0.1624	2.1373	1.4619
1.7933	16.0	32	1.5227	0.0575	1.5227	1.2340
1.7933	17.0	34	1.7374	0.1078	1.7374	1.3181
1.7933	18.0	36	2.0888	0.1489	2.0888	1.4453
1.7933	19.0	38	1.7404	0.1411	1.7404	1.3192
1.5013	20.0	40	1.8295	0.1288	1.8295	1.3526
1.5013	21.0	42	2.7252	0.0775	2.7252	1.6508
1.5013	22.0	44	2.2863	0.1148	2.2863	1.5121
1.5013	23.0	46	1.9034	0.1520	1.9034	1.3796
1.5013	24.0	48	2.4564	0.1052	2.4564	1.5673
1.0621	25.0	50	2.3437	0.1033	2.3437	1.5309
1.0621	26.0	52	2.8176	0.0791	2.8176	1.6786
1.0621	27.0	54	2.2993	0.1371	2.2993	1.5164
1.0621	28.0	56	3.3617	0.0554	3.3617	1.8335
1.0621	29.0	58	2.8583	0.0866	2.8583	1.6907
0.5724	30.0	60	2.0071	0.1854	2.0071	1.4167
0.5724	31.0	62	2.4842	0.1259	2.4842	1.5762
0.5724	32.0	64	3.6091	0.0536	3.6091	1.8998
0.5724	33.0	66	3.5167	0.0628	3.5167	1.8753
0.5724	34.0	68	2.4939	0.1330	2.4939	1.5792
0.3724	35.0	70	3.0914	0.0849	3.0914	1.7582
0.3724	36.0	72	2.7255	0.1191	2.7255	1.6509
0.3724	37.0	74	2.7631	0.1198	2.7631	1.6622
0.3724	38.0	76	2.6358	0.1352	2.6358	1.6235
0.3724	39.0	78	3.2364	0.0837	3.2364	1.7990
0.254	40.0	80	3.0060	0.0967	3.0059	1.7338
0.254	41.0	82	2.7999	0.1069	2.7999	1.6733
0.254	42.0	84	3.1689	0.0883	3.1689	1.7801
0.254	43.0	86	3.2822	0.0836	3.2822	1.8117
0.254	44.0	88	3.0970	0.0885	3.0970	1.7598
0.1736	45.0	90	2.5817	0.1349	2.5817	1.6068
0.1736	46.0	92	2.9280	0.1108	2.9280	1.7111
0.1736	47.0	94	2.9410	0.1154	2.9410	1.7149
0.1736	48.0	96	2.3168	0.1684	2.3168	1.5221
0.1736	49.0	98	2.4283	0.1632	2.4283	1.5583
0.1486	50.0	100	3.1574	0.1084	3.1574	1.7769
0.1486	51.0	102	2.9698	0.1068	2.9698	1.7233
0.1486	52.0	104	2.5049	0.1489	2.5049	1.5827
0.1486	53.0	106	3.1017	0.0877	3.1017	1.7612
0.1486	54.0	108	3.0418	0.0908	3.0418	1.7441
0.1233	55.0	110	2.4456	0.1517	2.4456	1.5639
0.1233	56.0	112	2.8118	0.1073	2.8118	1.6769
0.1233	57.0	114	2.7787	0.1210	2.7787	1.6669
0.1233	58.0	116	2.7518	0.1227	2.7518	1.6589
0.1233	59.0	118	2.7771	0.1209	2.7771	1.6665
0.1054	60.0	120	2.4018	0.1516	2.4018	1.5498
0.1054	61.0	122	2.5651	0.1327	2.5651	1.6016
0.1054	62.0	124	2.4406	0.1493	2.4406	1.5622
0.1054	63.0	126	2.8577	0.1144	2.8577	1.6905
0.1054	64.0	128	2.5507	0.1318	2.5507	1.5971
0.0981	65.0	130	2.0764	0.1847	2.0764	1.4410
0.0981	66.0	132	2.3426	0.1459	2.3426	1.5306
0.0981	67.0	134	3.0805	0.0948	3.0805	1.7551
0.0981	68.0	136	3.2191	0.0815	3.2191	1.7942
0.0981	69.0	138	2.6300	0.1184	2.6300	1.6217
0.1122	70.0	140	1.9715	0.2115	1.9715	1.4041
0.1122	71.0	142	2.0239	0.1938	2.0239	1.4226
0.1122	72.0	144	2.5947	0.1181	2.5947	1.6108
0.1122	73.0	146	2.8110	0.1127	2.8110	1.6766
0.1122	74.0	148	2.5182	0.1347	2.5182	1.5869
0.0899	75.0	150	2.6086	0.1365	2.6086	1.6151
0.0899	76.0	152	2.9564	0.1153	2.9564	1.7194
0.0899	77.0	154	2.7835	0.1342	2.7835	1.6684
0.0899	78.0	156	2.5104	0.1472	2.5104	1.5844
0.0899	79.0	158	2.6229	0.1391	2.6229	1.6195
0.0772	80.0	160	2.6771	0.1336	2.6771	1.6362
0.0772	81.0	162	2.6291	0.1312	2.6291	1.6214
0.0772	82.0	164	2.4204	0.1493	2.4204	1.5558
0.0772	83.0	166	2.3233	0.1581	2.3233	1.5242
0.0772	84.0	168	2.3747	0.1514	2.3747	1.5410
0.0771	85.0	170	2.5471	0.1405	2.5471	1.5960
0.0771	86.0	172	2.6281	0.1360	2.6281	1.6211
0.0771	87.0	174	2.5029	0.1520	2.5029	1.5821
0.0771	88.0	176	2.4189	0.1629	2.4189	1.5553
0.0771	89.0	178	2.5380	0.1522	2.5380	1.5931
0.0766	90.0	180	2.7065	0.1380	2.7065	1.6451
0.0766	91.0	182	2.6679	0.1351	2.6679	1.6334
0.0766	92.0	184	2.5639	0.1471	2.5639	1.6012
0.0766	93.0	186	2.5141	0.1511	2.5141	1.5856
0.0766	94.0	188	2.5017	0.1513	2.5017	1.5817
0.0521	95.0	190	2.5129	0.1508	2.5129	1.5852
0.0521	96.0	192	2.4979	0.1555	2.4979	1.5805
0.0521	97.0	194	2.4822	0.1628	2.4822	1.5755
0.0521	98.0	196	2.5032	0.1601	2.5032	1.5822
0.0521	99.0	198	2.5438	0.1584	2.5438	1.5949
0.0576	100.0	200	2.5672	0.1569	2.5672	1.6023

Framework versions

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