ASAP_FineTuningBERT_AugV5_k2_task1_organization_fold4

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: 1.9068
• Qwk: -0.0871
• Mse: 1.9068
• Rmse: 1.3809

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	10.6318	0.0026	10.6318	3.2606
No log	2.0	4	8.4386	0.0018	8.4386	2.9049
No log	3.0	6	6.7144	0.0018	6.7144	2.5912
No log	4.0	8	5.2728	0.0391	5.2728	2.2963
5.496	5.0	10	4.2280	0.0156	4.2280	2.0562
5.496	6.0	12	3.3525	0.0079	3.3525	1.8310
5.496	7.0	14	2.5522	0.0205	2.5522	1.5976
5.496	8.0	16	2.1207	0.1078	2.1207	1.4563
5.496	9.0	18	1.7779	0.0444	1.7779	1.3334
2.1751	10.0	20	1.5720	0.0420	1.5720	1.2538
2.1751	11.0	22	1.5498	0.0420	1.5498	1.2449
2.1751	12.0	24	1.3146	0.0212	1.3146	1.1465
2.1751	13.0	26	1.2870	0.0212	1.2870	1.1345
2.1751	14.0	28	1.5803	0.0046	1.5803	1.2571
1.7844	15.0	30	1.4139	0.0178	1.4139	1.1891
1.7844	16.0	32	1.1932	0.0238	1.1932	1.0924
1.7844	17.0	34	1.7132	-0.0259	1.7132	1.3089
1.7844	18.0	36	1.7338	-0.0357	1.7338	1.3167
1.7844	19.0	38	1.4304	-0.0112	1.4304	1.1960
1.2631	20.0	40	1.7332	-0.0444	1.7332	1.3165
1.2631	21.0	42	2.0796	-0.0714	2.0796	1.4421
1.2631	22.0	44	1.6976	-0.0270	1.6976	1.3029
1.2631	23.0	46	1.9982	-0.0946	1.9982	1.4136
1.2631	24.0	48	1.6551	-0.0515	1.6551	1.2865
0.6094	25.0	50	1.9776	-0.0588	1.9776	1.4063
0.6094	26.0	52	1.9061	-0.0848	1.9061	1.3806
0.6094	27.0	54	1.3901	-0.0514	1.3901	1.1790
0.6094	28.0	56	1.9364	-0.0710	1.9364	1.3915
0.6094	29.0	58	2.0385	-0.0801	2.0385	1.4277
0.3355	30.0	60	1.4299	-0.0645	1.4299	1.1958
0.3355	31.0	62	1.5245	-0.0850	1.5245	1.2347
0.3355	32.0	64	2.2822	-0.1118	2.2822	1.5107
0.3355	33.0	66	2.0794	-0.1143	2.0794	1.4420
0.3355	34.0	68	1.7600	-0.1230	1.7600	1.3267
0.2183	35.0	70	2.4782	-0.1351	2.4782	1.5742
0.2183	36.0	72	2.5393	-0.1433	2.5393	1.5935
0.2183	37.0	74	1.7955	-0.1146	1.7955	1.3400
0.2183	38.0	76	1.7914	-0.1167	1.7914	1.3384
0.2183	39.0	78	2.1912	-0.1112	2.1912	1.4803
0.1871	40.0	80	1.9314	-0.1100	1.9314	1.3897
0.1871	41.0	82	1.8203	-0.1103	1.8203	1.3492
0.1871	42.0	84	2.0008	-0.1044	2.0008	1.4145
0.1871	43.0	86	2.2055	-0.0943	2.2055	1.4851
0.1871	44.0	88	2.0233	-0.0943	2.0233	1.4224
0.107	45.0	90	1.6122	-0.0854	1.6122	1.2697
0.107	46.0	92	1.7915	-0.1136	1.7915	1.3385
0.107	47.0	94	2.3185	-0.1119	2.3185	1.5227
0.107	48.0	96	2.0651	-0.0926	2.0651	1.4371
0.107	49.0	98	1.5548	-0.0895	1.5548	1.2469
0.1598	50.0	100	1.5350	-0.0826	1.5350	1.2390
0.1598	51.0	102	1.9385	-0.1104	1.9385	1.3923
0.1598	52.0	104	2.2863	-0.1051	2.2863	1.5121
0.1598	53.0	106	1.9998	-0.1165	1.9998	1.4141
0.1598	54.0	108	1.7690	-0.0894	1.7690	1.3300
0.1154	55.0	110	1.9243	-0.0739	1.9243	1.3872
0.1154	56.0	112	2.0876	-0.0923	2.0876	1.4448
0.1154	57.0	114	2.0650	-0.0864	2.0650	1.4370
0.1154	58.0	116	1.8476	-0.0572	1.8476	1.3592
0.1154	59.0	118	1.8643	-0.0631	1.8643	1.3654
0.0781	60.0	120	2.0839	-0.0647	2.0839	1.4436
0.0781	61.0	122	1.9337	-0.0703	1.9337	1.3906
0.0781	62.0	124	1.9155	-0.0692	1.9155	1.3840
0.0781	63.0	126	1.9222	-0.0708	1.9222	1.3864
0.0781	64.0	128	1.8361	-0.1008	1.8361	1.3550
0.0858	65.0	130	2.0123	-0.0852	2.0123	1.4185
0.0858	66.0	132	1.9921	-0.0885	1.9921	1.4114
0.0858	67.0	134	1.9462	-0.1032	1.9462	1.3951
0.0858	68.0	136	1.8214	-0.1001	1.8214	1.3496
0.0858	69.0	138	1.8356	-0.0973	1.8356	1.3548
0.0674	70.0	140	1.9821	-0.0733	1.9821	1.4079
0.0674	71.0	142	2.1978	-0.1060	2.1978	1.4825
0.0674	72.0	144	2.0422	-0.0747	2.0422	1.4291
0.0674	73.0	146	1.8078	-0.0725	1.8078	1.3445
0.0674	74.0	148	1.8364	-0.0645	1.8364	1.3551
0.0682	75.0	150	2.0396	-0.0786	2.0396	1.4281
0.0682	76.0	152	2.0517	-0.0788	2.0517	1.4324
0.0682	77.0	154	1.8596	-0.0708	1.8596	1.3637
0.0682	78.0	156	1.8009	-0.0743	1.8009	1.3420
0.0682	79.0	158	1.8874	-0.0778	1.8874	1.3738
0.0559	80.0	160	2.0043	-0.0919	2.0043	1.4157
0.0559	81.0	162	1.9238	-0.0796	1.9238	1.3870
0.0559	82.0	164	1.7809	-0.0650	1.7809	1.3345
0.0559	83.0	166	1.8109	-0.0762	1.8109	1.3457
0.0559	84.0	168	1.9396	-0.0819	1.9396	1.3927
0.0517	85.0	170	1.9774	-0.0836	1.9774	1.4062
0.0517	86.0	172	1.8979	-0.0888	1.8979	1.3776
0.0517	87.0	174	1.8175	-0.0727	1.8175	1.3481
0.0517	88.0	176	1.8569	-0.0720	1.8569	1.3627
0.0517	89.0	178	1.8994	-0.0958	1.8994	1.3782
0.0585	90.0	180	1.9564	-0.0899	1.9564	1.3987
0.0585	91.0	182	1.9520	-0.0958	1.9520	1.3972
0.0585	92.0	184	1.8851	-0.0868	1.8851	1.3730
0.0585	93.0	186	1.8087	-0.0736	1.8087	1.3449
0.0585	94.0	188	1.7820	-0.0737	1.7820	1.3349
0.0541	95.0	190	1.7973	-0.0777	1.7973	1.3406
0.0541	96.0	192	1.8206	-0.0835	1.8206	1.3493
0.0541	97.0	194	1.8549	-0.0845	1.8549	1.3620
0.0541	98.0	196	1.8897	-0.0922	1.8897	1.3747
0.0541	99.0	198	1.9029	-0.0871	1.9029	1.3794
0.0547	100.0	200	1.9068	-0.0871	1.9068	1.3809

Framework versions

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