ASAP_FineTuningBERT_AugV7_k4_task1_organization_fold3

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: 0.6077
• Qwk: 0.5940
• Mse: 0.6076
• Rmse: 0.7795

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	0.5	2	11.9186	0.0042	11.9176	3.4522
No log	1.0	4	11.0555	0.0	11.0546	3.3248
No log	1.5	6	10.3443	0.0	10.3434	3.2161
No log	2.0	8	9.1503	0.0	9.1496	3.0248
7.95	2.5	10	7.7523	0.0	7.7517	2.7842
7.95	3.0	12	6.5038	0.0	6.5034	2.5502
7.95	3.5	14	5.3279	0.0100	5.3277	2.3082
7.95	4.0	16	4.3354	0.0	4.3354	2.0822
7.95	4.5	18	3.4230	0.0	3.4231	1.8502
3.7555	5.0	20	2.6991	0.0020	2.6994	1.6430
3.7555	5.5	22	1.9863	0.0417	1.9868	1.4095
3.7555	6.0	24	1.6689	0.0202	1.6696	1.2921
3.7555	6.5	26	1.2180	0.0202	1.2188	1.1040
3.7555	7.0	28	1.0282	0.0102	1.0291	1.0144
1.9875	7.5	30	1.1562	0.0202	1.1569	1.0756
1.9875	8.0	32	1.4171	0.0266	1.4178	1.1907
1.9875	8.5	34	0.9851	0.0202	0.9858	0.9929
1.9875	9.0	36	1.0941	0.0266	1.0948	1.0463
1.9875	9.5	38	1.2864	0.0488	1.2868	1.1344
1.8299	10.0	40	1.8665	0.1872	1.8667	1.3663
1.8299	10.5	42	1.9895	0.2004	1.9897	1.4106
1.8299	11.0	44	1.4788	0.1334	1.4791	1.2162
1.8299	11.5	46	1.0294	0.0452	1.0300	1.0149
1.8299	12.0	48	0.9327	0.0370	0.9333	0.9661
1.6502	12.5	50	1.1579	0.1209	1.1583	1.0763
1.6502	13.0	52	0.9949	0.2504	0.9953	0.9976
1.6502	13.5	54	0.7086	0.4350	0.7090	0.8420
1.6502	14.0	56	0.6737	0.4530	0.6741	0.8210
1.6502	14.5	58	0.9152	0.3450	0.9156	0.9569
1.1337	15.0	60	0.6551	0.4738	0.6555	0.8096
1.1337	15.5	62	0.6160	0.4744	0.6164	0.7851
1.1337	16.0	64	0.6073	0.4683	0.6075	0.7794
1.1337	16.5	66	0.6035	0.4724	0.6037	0.7770
1.1337	17.0	68	0.5918	0.4866	0.5920	0.7694
0.6241	17.5	70	0.5772	0.5287	0.5772	0.7598
0.6241	18.0	72	0.6116	0.5399	0.6116	0.7820
0.6241	18.5	74	0.6222	0.5432	0.6221	0.7888
0.6241	19.0	76	0.5815	0.5386	0.5815	0.7626
0.6241	19.5	78	0.6059	0.5272	0.6060	0.7784
0.36	20.0	80	0.5677	0.5936	0.5676	0.7534
0.36	20.5	82	0.5690	0.5829	0.5688	0.7542
0.36	21.0	84	0.6580	0.5666	0.6580	0.8112
0.36	21.5	86	0.5505	0.6096	0.5505	0.7419
0.36	22.0	88	0.5503	0.6075	0.5502	0.7417
0.2302	22.5	90	0.6531	0.5743	0.6530	0.8081
0.2302	23.0	92	0.6696	0.5764	0.6695	0.8182
0.2302	23.5	94	0.6632	0.6027	0.6629	0.8142
0.2302	24.0	96	0.6370	0.6122	0.6368	0.7980
0.2302	24.5	98	0.6497	0.5864	0.6496	0.8060
0.2804	25.0	100	0.6600	0.5752	0.6599	0.8123
0.2804	25.5	102	0.6243	0.6206	0.6241	0.7900
0.2804	26.0	104	0.6175	0.6091	0.6173	0.7857
0.2804	26.5	106	0.6770	0.5740	0.6770	0.8228
0.2804	27.0	108	0.7705	0.5213	0.7705	0.8778
0.2057	27.5	110	0.6005	0.5994	0.6004	0.7749
0.2057	28.0	112	0.7007	0.5942	0.7005	0.8369
0.2057	28.5	114	0.6249	0.5724	0.6248	0.7905
0.2057	29.0	116	0.6205	0.5763	0.6204	0.7877
0.2057	29.5	118	0.6213	0.6011	0.6211	0.7881
0.1334	30.0	120	0.5910	0.5982	0.5909	0.7687
0.1334	30.5	122	0.6293	0.5643	0.6294	0.7933
0.1334	31.0	124	0.6281	0.5778	0.6281	0.7926
0.1334	31.5	126	0.6542	0.6032	0.6540	0.8087
0.1334	32.0	128	0.6965	0.5891	0.6962	0.8344
0.1412	32.5	130	0.6114	0.5754	0.6113	0.7819
0.1412	33.0	132	0.6531	0.5704	0.6531	0.8081
0.1412	33.5	134	0.5739	0.6126	0.5738	0.7575
0.1412	34.0	136	0.5704	0.5947	0.5704	0.7552
0.1412	34.5	138	0.6076	0.5727	0.6076	0.7795
0.1287	35.0	140	0.6102	0.5841	0.6101	0.7811
0.1287	35.5	142	0.6537	0.5965	0.6535	0.8084
0.1287	36.0	144	0.6048	0.5816	0.6047	0.7776
0.1287	36.5	146	0.5938	0.5806	0.5937	0.7705
0.1287	37.0	148	0.6102	0.6085	0.6102	0.7811
0.0854	37.5	150	0.6248	0.5782	0.6248	0.7904
0.0854	38.0	152	0.6074	0.5818	0.6074	0.7793
0.0854	38.5	154	0.6278	0.5637	0.6278	0.7924
0.0854	39.0	156	0.5971	0.5959	0.5971	0.7727
0.0854	39.5	158	0.6145	0.6173	0.6143	0.7838
0.0683	40.0	160	0.6080	0.5964	0.6078	0.7796
0.0683	40.5	162	0.6593	0.5905	0.6589	0.8117
0.0683	41.0	164	0.7628	0.5737	0.7623	0.8731
0.0683	41.5	166	0.7029	0.5942	0.7026	0.8382
0.0683	42.0	168	0.6402	0.5900	0.6402	0.8001
0.0872	42.5	170	0.6252	0.5833	0.6250	0.7906
0.0872	43.0	172	0.6105	0.5896	0.6104	0.7813
0.0872	43.5	174	0.6138	0.5652	0.6138	0.7835
0.0872	44.0	176	0.6178	0.6179	0.6177	0.7859
0.0872	44.5	178	0.6174	0.5982	0.6173	0.7857
0.0677	45.0	180	0.6618	0.5728	0.6619	0.8136
0.0677	45.5	182	0.6300	0.5692	0.6300	0.7937
0.0677	46.0	184	0.6189	0.6292	0.6188	0.7866
0.0677	46.5	186	0.6048	0.5647	0.6048	0.7777
0.0677	47.0	188	0.6448	0.5605	0.6449	0.8031
0.078	47.5	190	0.6202	0.5794	0.6202	0.7875
0.078	48.0	192	0.6269	0.6052	0.6268	0.7917
0.078	48.5	194	0.6227	0.5976	0.6225	0.7890
0.078	49.0	196	0.6072	0.5636	0.6072	0.7792
0.078	49.5	198	0.6055	0.5712	0.6054	0.7781
0.0665	50.0	200	0.6964	0.5901	0.6961	0.8343
0.0665	50.5	202	0.6540	0.5942	0.6538	0.8086
0.0665	51.0	204	0.6372	0.5862	0.6372	0.7982
0.0665	51.5	206	0.6206	0.5714	0.6205	0.7877
0.0665	52.0	208	0.6253	0.6102	0.6251	0.7906
0.0776	52.5	210	0.6138	0.5958	0.6136	0.7833
0.0776	53.0	212	0.6203	0.5770	0.6204	0.7876
0.0776	53.5	214	0.5929	0.5777	0.5929	0.7700
0.0776	54.0	216	0.5842	0.5631	0.5842	0.7643
0.0776	54.5	218	0.6003	0.5694	0.6003	0.7748
0.0456	55.0	220	0.6360	0.5763	0.6360	0.7975
0.0456	55.5	222	0.6212	0.5687	0.6212	0.7882
0.0456	56.0	224	0.6504	0.5978	0.6503	0.8064
0.0456	56.5	226	0.6296	0.5755	0.6295	0.7934
0.0456	57.0	228	0.6079	0.5780	0.6078	0.7796
0.0554	57.5	230	0.5930	0.5724	0.5928	0.7700
0.0554	58.0	232	0.6127	0.5949	0.6125	0.7826
0.0554	58.5	234	0.6032	0.5664	0.6031	0.7766
0.0554	59.0	236	0.6427	0.5826	0.6427	0.8017
0.0554	59.5	238	0.6515	0.5838	0.6516	0.8072
0.0643	60.0	240	0.6456	0.5834	0.6456	0.8035
0.0643	60.5	242	0.6164	0.5900	0.6164	0.7851
0.0643	61.0	244	0.6128	0.5743	0.6129	0.7829
0.0643	61.5	246	0.5910	0.5817	0.5910	0.7688
0.0643	62.0	248	0.5796	0.6021	0.5795	0.7613
0.0555	62.5	250	0.5938	0.6029	0.5938	0.7706
0.0555	63.0	252	0.6085	0.6044	0.6085	0.7800
0.0555	63.5	254	0.6186	0.5919	0.6186	0.7865
0.0555	64.0	256	0.6084	0.6008	0.6083	0.7799
0.0555	64.5	258	0.6034	0.5922	0.6032	0.7767
0.0479	65.0	260	0.6211	0.5725	0.6209	0.7880
0.0479	65.5	262	0.6410	0.5964	0.6407	0.8005
0.0479	66.0	264	0.6302	0.5803	0.6300	0.7937
0.0479	66.5	266	0.6088	0.5774	0.6087	0.7802
0.0479	67.0	268	0.6029	0.5794	0.6028	0.7764
0.0463	67.5	270	0.6046	0.5804	0.6045	0.7775
0.0463	68.0	272	0.6012	0.5858	0.6011	0.7753
0.0463	68.5	274	0.6063	0.5738	0.6063	0.7786
0.0463	69.0	276	0.6123	0.5835	0.6123	0.7825
0.0463	69.5	278	0.6226	0.5847	0.6225	0.7890
0.0489	70.0	280	0.6332	0.5873	0.6331	0.7957
0.0489	70.5	282	0.6179	0.5745	0.6178	0.7860
0.0489	71.0	284	0.6219	0.5658	0.6218	0.7886
0.0489	71.5	286	0.6270	0.5796	0.6269	0.7918
0.0489	72.0	288	0.6166	0.5943	0.6165	0.7852
0.0487	72.5	290	0.6039	0.5680	0.6039	0.7771
0.0487	73.0	292	0.6115	0.5709	0.6115	0.7820
0.0487	73.5	294	0.6079	0.5705	0.6079	0.7797
0.0487	74.0	296	0.6035	0.5826	0.6035	0.7769
0.0487	74.5	298	0.6077	0.5728	0.6077	0.7795
0.0452	75.0	300	0.6084	0.5655	0.6084	0.7800
0.0452	75.5	302	0.5934	0.5720	0.5933	0.7703
0.0452	76.0	304	0.6003	0.5860	0.6002	0.7747
0.0452	76.5	306	0.6074	0.5928	0.6073	0.7793
0.0452	77.0	308	0.6329	0.5817	0.6328	0.7955
0.04	77.5	310	0.6311	0.5879	0.6310	0.7944
0.04	78.0	312	0.6131	0.5694	0.6130	0.7829
0.04	78.5	314	0.6065	0.5667	0.6064	0.7787
0.04	79.0	316	0.6158	0.5917	0.6157	0.7846
0.04	79.5	318	0.6177	0.5976	0.6176	0.7859
0.0383	80.0	320	0.6009	0.5976	0.6008	0.7751
0.0383	80.5	322	0.6020	0.5726	0.6020	0.7759
0.0383	81.0	324	0.6057	0.5753	0.6057	0.7783
0.0383	81.5	326	0.6038	0.5950	0.6037	0.7770
0.0383	82.0	328	0.6001	0.5666	0.6001	0.7747
0.0359	82.5	330	0.5931	0.5924	0.5930	0.7701
0.0359	83.0	332	0.5912	0.5812	0.5911	0.7689
0.0359	83.5	334	0.5976	0.5700	0.5976	0.7730
0.0359	84.0	336	0.6043	0.5718	0.6043	0.7774
0.0359	84.5	338	0.6059	0.5975	0.6059	0.7784
0.0407	85.0	340	0.6169	0.6054	0.6168	0.7854
0.0407	85.5	342	0.6139	0.6028	0.6138	0.7835
0.0407	86.0	344	0.6066	0.5800	0.6065	0.7788
0.0407	86.5	346	0.6096	0.5729	0.6096	0.7808
0.0407	87.0	348	0.6082	0.5728	0.6082	0.7798
0.0374	87.5	350	0.6088	0.5915	0.6087	0.7802
0.0374	88.0	352	0.6148	0.5991	0.6147	0.7840
0.0374	88.5	354	0.6168	0.5928	0.6168	0.7853
0.0374	89.0	356	0.6160	0.5819	0.6159	0.7848
0.0374	89.5	358	0.6123	0.5889	0.6122	0.7824
0.0358	90.0	360	0.6072	0.5960	0.6071	0.7792
0.0358	90.5	362	0.6039	0.5785	0.6039	0.7771
0.0358	91.0	364	0.6052	0.5571	0.6052	0.7779
0.0358	91.5	366	0.6040	0.5584	0.6039	0.7771
0.0358	92.0	368	0.6023	0.5603	0.6023	0.7761
0.0375	92.5	370	0.6043	0.5732	0.6043	0.7774
0.0375	93.0	372	0.6056	0.5725	0.6056	0.7782
0.0375	93.5	374	0.6076	0.5877	0.6075	0.7795
0.0375	94.0	376	0.6115	0.6001	0.6114	0.7819
0.0375	94.5	378	0.6143	0.5961	0.6143	0.7838
0.0325	95.0	380	0.6148	0.5967	0.6147	0.7840
0.0325	95.5	382	0.6139	0.5948	0.6138	0.7835
0.0325	96.0	384	0.6133	0.5820	0.6133	0.7831
0.0325	96.5	386	0.6127	0.5696	0.6127	0.7827
0.0325	97.0	388	0.6108	0.5721	0.6108	0.7815
0.0326	97.5	390	0.6086	0.5734	0.6086	0.7801
0.0326	98.0	392	0.6075	0.5904	0.6074	0.7794
0.0326	98.5	394	0.6074	0.5868	0.6074	0.7793
0.0326	99.0	396	0.6076	0.5887	0.6075	0.7794
0.0326	99.5	398	0.6077	0.5940	0.6076	0.7795
0.0344	100.0	400	0.6077	0.5940	0.6076	0.7795

Framework versions

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