ASAP_FineTuningBERT_Aug_k1_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: 0.5390
• Qwk: 0.6614
• Mse: 0.5390
• Rmse: 0.7342

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0417	2	10.9663	0.0	10.9663	3.3115
No log	0.0833	4	9.4263	0.0	9.4263	3.0702
No log	0.125	6	7.8318	0.0107	7.8318	2.7985
No log	0.1667	8	6.2699	0.0023	6.2699	2.5040
No log	0.2083	10	4.7637	0.0	4.7637	2.1826
No log	0.25	12	3.4917	0.0297	3.4917	1.8686
No log	0.2917	14	2.4523	0.0147	2.4523	1.5660
No log	0.3333	16	1.7750	0.0086	1.7750	1.3323
No log	0.375	18	1.3127	0.0943	1.3127	1.1457
No log	0.4167	20	0.9924	0.0524	0.9924	0.9962
No log	0.4583	22	0.8882	0.0266	0.8882	0.9424
No log	0.5	24	0.8485	0.0102	0.8485	0.9211
No log	0.5417	26	0.8307	0.0671	0.8307	0.9114
No log	0.5833	28	0.8599	0.3386	0.8599	0.9273
No log	0.625	30	0.8520	0.1542	0.8520	0.9230
No log	0.6667	32	0.8203	0.0284	0.8203	0.9057
No log	0.7083	34	0.7727	0.0384	0.7727	0.8790
No log	0.75	36	0.6904	0.1335	0.6904	0.8309
No log	0.7917	38	0.7254	0.4371	0.7254	0.8517
No log	0.8333	40	0.6569	0.2662	0.6569	0.8105
No log	0.875	42	0.7216	0.1294	0.7216	0.8495
No log	0.9167	44	0.6092	0.2773	0.6092	0.7805
No log	0.9583	46	0.6772	0.4222	0.6772	0.8229
No log	1.0	48	0.6767	0.4602	0.6767	0.8226
No log	1.0417	50	0.5863	0.4008	0.5863	0.7657
No log	1.0833	52	0.6300	0.2867	0.6300	0.7937
No log	1.125	54	0.5294	0.4568	0.5294	0.7276
No log	1.1667	56	0.6231	0.5171	0.6231	0.7894
No log	1.2083	58	0.6013	0.5343	0.6013	0.7754
No log	1.25	60	0.4991	0.5050	0.4991	0.7064
No log	1.2917	62	0.4922	0.4875	0.4922	0.7016
No log	1.3333	64	0.5272	0.5453	0.5272	0.7261
No log	1.375	66	0.6860	0.5477	0.6860	0.8283
No log	1.4167	68	0.5690	0.5617	0.5690	0.7544
No log	1.4583	70	0.4874	0.5123	0.4874	0.6981
No log	1.5	72	0.5300	0.5974	0.5300	0.7280
No log	1.5417	74	0.5168	0.5891	0.5168	0.7189
No log	1.5833	76	0.4533	0.5359	0.4533	0.6733
No log	1.625	78	0.4715	0.5613	0.4715	0.6867
No log	1.6667	80	0.7300	0.5520	0.7300	0.8544
No log	1.7083	82	0.8602	0.4575	0.8602	0.9275
No log	1.75	84	0.6119	0.5794	0.6119	0.7822
No log	1.7917	86	0.4616	0.5208	0.4616	0.6794
No log	1.8333	88	0.4639	0.5281	0.4639	0.6811
No log	1.875	90	0.5099	0.5767	0.5099	0.7141
No log	1.9167	92	0.5564	0.5809	0.5564	0.7459
No log	1.9583	94	0.4995	0.5813	0.4995	0.7068
No log	2.0	96	0.4406	0.5330	0.4406	0.6638
No log	2.0417	98	0.4350	0.5189	0.4350	0.6596
No log	2.0833	100	0.4884	0.6066	0.4884	0.6989
No log	2.125	102	0.6504	0.6157	0.6504	0.8065
No log	2.1667	104	0.5399	0.6087	0.5399	0.7348
No log	2.2083	106	0.4432	0.5703	0.4432	0.6657
No log	2.25	108	0.4776	0.5874	0.4776	0.6911
No log	2.2917	110	0.6471	0.6155	0.6471	0.8044
No log	2.3333	112	0.5459	0.6019	0.5459	0.7388
No log	2.375	114	0.4922	0.6038	0.4922	0.7015
No log	2.4167	116	0.4859	0.6087	0.4859	0.6970
No log	2.4583	118	0.5212	0.6050	0.5212	0.7219
No log	2.5	120	0.5050	0.6037	0.5050	0.7107
No log	2.5417	122	0.4367	0.5864	0.4367	0.6608
No log	2.5833	124	0.4564	0.5931	0.4564	0.6756
No log	2.625	126	0.5612	0.6236	0.5612	0.7491
No log	2.6667	128	0.5660	0.6258	0.5660	0.7523
No log	2.7083	130	0.5733	0.6258	0.5733	0.7572
No log	2.75	132	0.4220	0.5608	0.4220	0.6496
No log	2.7917	134	0.4163	0.5664	0.4163	0.6452
No log	2.8333	136	0.4847	0.6089	0.4847	0.6962
No log	2.875	138	0.5050	0.6149	0.5050	0.7106
No log	2.9167	140	0.4212	0.5688	0.4212	0.6490
No log	2.9583	142	0.4243	0.5630	0.4243	0.6514
No log	3.0	144	0.4711	0.6060	0.4711	0.6864
No log	3.0417	146	0.4862	0.6030	0.4862	0.6973
No log	3.0833	148	0.4597	0.5956	0.4597	0.6780
No log	3.125	150	0.5160	0.6132	0.5160	0.7183
No log	3.1667	152	0.4906	0.6138	0.4906	0.7004
No log	3.2083	154	0.4656	0.5938	0.4656	0.6823
No log	3.25	156	0.5141	0.6151	0.5141	0.7170
No log	3.2917	158	0.5455	0.6226	0.5455	0.7386
No log	3.3333	160	0.4454	0.5889	0.4454	0.6673
No log	3.375	162	0.4323	0.5770	0.4323	0.6575
No log	3.4167	164	0.4546	0.6201	0.4546	0.6742
No log	3.4583	166	0.4639	0.6152	0.4639	0.6811
No log	3.5	168	0.4446	0.6008	0.4446	0.6668
No log	3.5417	170	0.4840	0.6321	0.4840	0.6957
No log	3.5833	172	0.4297	0.5647	0.4297	0.6555
No log	3.625	174	0.4354	0.5633	0.4354	0.6599
No log	3.6667	176	0.5103	0.5973	0.5103	0.7144
No log	3.7083	178	0.4955	0.6006	0.4955	0.7039
No log	3.75	180	0.4306	0.5592	0.4306	0.6562
No log	3.7917	182	0.4554	0.5867	0.4554	0.6748
No log	3.8333	184	0.6762	0.6240	0.6762	0.8223
No log	3.875	186	0.7220	0.6492	0.7220	0.8497
No log	3.9167	188	0.5116	0.6655	0.5116	0.7153
No log	3.9583	190	0.4229	0.5645	0.4229	0.6503
No log	4.0	192	0.4209	0.5723	0.4209	0.6488
No log	4.0417	194	0.4975	0.6697	0.4975	0.7053
No log	4.0833	196	0.5781	0.6848	0.5781	0.7603
No log	4.125	198	0.4780	0.6700	0.4780	0.6914
No log	4.1667	200	0.4190	0.5819	0.4190	0.6473
No log	4.2083	202	0.4450	0.6422	0.4450	0.6671
No log	4.25	204	0.5491	0.6498	0.5491	0.7410
No log	4.2917	206	0.5386	0.6348	0.5386	0.7339
No log	4.3333	208	0.4654	0.6148	0.4654	0.6822
No log	4.375	210	0.4679	0.6148	0.4679	0.6840
No log	4.4167	212	0.5931	0.6221	0.5931	0.7701
No log	4.4583	214	0.5860	0.6314	0.5860	0.7655
No log	4.5	216	0.4750	0.6139	0.4750	0.6892
No log	4.5417	218	0.4833	0.6165	0.4833	0.6952
No log	4.5833	220	0.5171	0.6415	0.5171	0.7191
No log	4.625	222	0.4802	0.6328	0.4802	0.6929
No log	4.6667	224	0.4484	0.6444	0.4484	0.6696
No log	4.7083	226	0.4427	0.6380	0.4427	0.6654
No log	4.75	228	0.5483	0.6700	0.5483	0.7405
No log	4.7917	230	0.5746	0.6688	0.5746	0.7580
No log	4.8333	232	0.4564	0.6306	0.4564	0.6756
No log	4.875	234	0.4311	0.6119	0.4311	0.6566
No log	4.9167	236	0.4561	0.6395	0.4561	0.6754
No log	4.9583	238	0.4414	0.6159	0.4414	0.6644
No log	5.0	240	0.4686	0.6470	0.4686	0.6845
No log	5.0417	242	0.5663	0.6871	0.5663	0.7525
No log	5.0833	244	0.6179	0.6762	0.6179	0.7861
No log	5.125	246	0.5064	0.6726	0.5064	0.7116
No log	5.1667	248	0.4723	0.6460	0.4723	0.6872
No log	5.2083	250	0.5523	0.6694	0.5523	0.7432
No log	5.25	252	0.6151	0.6813	0.6151	0.7843
No log	5.2917	254	0.5367	0.6497	0.5367	0.7326
No log	5.3333	256	0.5388	0.6411	0.5388	0.7341
No log	5.375	258	0.4877	0.6165	0.4877	0.6984
No log	5.4167	260	0.4693	0.6180	0.4693	0.6851
No log	5.4583	262	0.4477	0.5763	0.4477	0.6691
No log	5.5	264	0.4621	0.6193	0.4621	0.6798
No log	5.5417	266	0.6466	0.6612	0.6466	0.8041
No log	5.5833	268	0.7448	0.6600	0.7448	0.8630
No log	5.625	270	0.5929	0.6752	0.5929	0.7700
No log	5.6667	272	0.4553	0.6205	0.4553	0.6747
No log	5.7083	274	0.4414	0.5916	0.4414	0.6644
No log	5.75	276	0.4653	0.6376	0.4653	0.6821
No log	5.7917	278	0.5432	0.6733	0.5432	0.7370
No log	5.8333	280	0.4844	0.6550	0.4844	0.6960
No log	5.875	282	0.4612	0.6536	0.4612	0.6791
No log	5.9167	284	0.5200	0.6652	0.5200	0.7211
No log	5.9583	286	0.5399	0.6756	0.5399	0.7348
No log	6.0	288	0.4445	0.6544	0.4445	0.6667
No log	6.0417	290	0.4349	0.6428	0.4349	0.6595
No log	6.0833	292	0.4856	0.6623	0.4856	0.6969
No log	6.125	294	0.5212	0.6643	0.5212	0.7220
No log	6.1667	296	0.5556	0.6713	0.5556	0.7454
No log	6.2083	298	0.5579	0.6744	0.5579	0.7469
No log	6.25	300	0.5715	0.6729	0.5715	0.7560
No log	6.2917	302	0.5541	0.6535	0.5541	0.7444
No log	6.3333	304	0.4756	0.6248	0.4756	0.6896
No log	6.375	306	0.4754	0.6285	0.4754	0.6895
No log	6.4167	308	0.5538	0.6415	0.5538	0.7442
No log	6.4583	310	0.6286	0.6692	0.6286	0.7928
No log	6.5	312	0.5390	0.6652	0.5390	0.7341
No log	6.5417	314	0.4593	0.6257	0.4593	0.6777
No log	6.5833	316	0.4511	0.6171	0.4511	0.6716
No log	6.625	318	0.5005	0.6571	0.5005	0.7074
No log	6.6667	320	0.5767	0.6701	0.5767	0.7594
No log	6.7083	322	0.5198	0.6638	0.5198	0.7210
No log	6.75	324	0.4540	0.6264	0.4540	0.6738
No log	6.7917	326	0.4702	0.6484	0.4702	0.6857
No log	6.8333	328	0.5826	0.6861	0.5826	0.7633
No log	6.875	330	0.5976	0.6852	0.5976	0.7730
No log	6.9167	332	0.4934	0.6673	0.4934	0.7024
No log	6.9583	334	0.4595	0.6324	0.4595	0.6778
No log	7.0	336	0.4497	0.6225	0.4497	0.6706
No log	7.0417	338	0.4966	0.6641	0.4966	0.7047
No log	7.0833	340	0.5630	0.6798	0.5630	0.7503
No log	7.125	342	0.5192	0.6620	0.5192	0.7205
No log	7.1667	344	0.4929	0.6492	0.4929	0.7021
No log	7.2083	346	0.4977	0.6486	0.4977	0.7055
No log	7.25	348	0.5401	0.6591	0.5401	0.7349
No log	7.2917	350	0.5409	0.6573	0.5409	0.7355
No log	7.3333	352	0.5271	0.6597	0.5271	0.7260
No log	7.375	354	0.5172	0.6672	0.5172	0.7192
No log	7.4167	356	0.4892	0.6412	0.4892	0.6994
No log	7.4583	358	0.4835	0.6341	0.4835	0.6954
No log	7.5	360	0.5130	0.6539	0.5130	0.7162
No log	7.5417	362	0.4942	0.6515	0.4942	0.7030
No log	7.5833	364	0.5067	0.6479	0.5067	0.7118
No log	7.625	366	0.4850	0.6355	0.4850	0.6964
No log	7.6667	368	0.4828	0.6292	0.4828	0.6948
No log	7.7083	370	0.5140	0.6396	0.5140	0.7170
No log	7.75	372	0.4916	0.6441	0.4916	0.7011
No log	7.7917	374	0.5074	0.6517	0.5074	0.7123
No log	7.8333	376	0.4879	0.6469	0.4879	0.6985
No log	7.875	378	0.4975	0.6534	0.4975	0.7053
No log	7.9167	380	0.5277	0.6740	0.5277	0.7264
No log	7.9583	382	0.5237	0.6731	0.5237	0.7237
No log	8.0	384	0.4924	0.6387	0.4924	0.7017
No log	8.0417	386	0.5033	0.6508	0.5033	0.7094
No log	8.0833	388	0.5438	0.6672	0.5438	0.7374
No log	8.125	390	0.5496	0.6694	0.5496	0.7414
No log	8.1667	392	0.5193	0.6558	0.5193	0.7206
No log	8.2083	394	0.4974	0.6466	0.4974	0.7053
No log	8.25	396	0.5203	0.6598	0.5203	0.7213
No log	8.2917	398	0.5464	0.6725	0.5464	0.7392
No log	8.3333	400	0.6041	0.6647	0.6041	0.7773
No log	8.375	402	0.5957	0.6613	0.5957	0.7718
No log	8.4167	404	0.5261	0.6652	0.5261	0.7253
No log	8.4583	406	0.5031	0.6539	0.5031	0.7093
No log	8.5	408	0.5218	0.6700	0.5218	0.7224
No log	8.5417	410	0.5461	0.6720	0.5461	0.7390
No log	8.5833	412	0.5460	0.6680	0.5460	0.7389
No log	8.625	414	0.5369	0.6681	0.5369	0.7328
No log	8.6667	416	0.5298	0.6682	0.5298	0.7279
No log	8.7083	418	0.5049	0.6496	0.5049	0.7105
No log	8.75	420	0.5070	0.6496	0.5070	0.7121
No log	8.7917	422	0.5086	0.6488	0.5086	0.7132
No log	8.8333	424	0.5253	0.6690	0.5253	0.7248
No log	8.875	426	0.5510	0.6687	0.5510	0.7423
No log	8.9167	428	0.5398	0.6672	0.5398	0.7347
No log	8.9583	430	0.5225	0.6566	0.5225	0.7229
No log	9.0	432	0.5242	0.6608	0.5242	0.7240
No log	9.0417	434	0.5489	0.6668	0.5489	0.7409
No log	9.0833	436	0.5800	0.6581	0.5800	0.7616
No log	9.125	438	0.5713	0.6610	0.5713	0.7558
No log	9.1667	440	0.5635	0.6589	0.5635	0.7507
No log	9.2083	442	0.5509	0.6675	0.5509	0.7422
No log	9.25	444	0.5367	0.6614	0.5367	0.7326
No log	9.2917	446	0.5247	0.6556	0.5247	0.7243
No log	9.3333	448	0.5287	0.6602	0.5287	0.7271
No log	9.375	450	0.5260	0.6551	0.5260	0.7253
No log	9.4167	452	0.5370	0.6640	0.5370	0.7328
No log	9.4583	454	0.5412	0.6664	0.5412	0.7357
No log	9.5	456	0.5438	0.6636	0.5438	0.7374
No log	9.5417	458	0.5368	0.6650	0.5368	0.7327
No log	9.5833	460	0.5373	0.6650	0.5373	0.7330
No log	9.625	462	0.5335	0.6626	0.5335	0.7304
No log	9.6667	464	0.5301	0.6633	0.5301	0.7281
No log	9.7083	466	0.5316	0.6626	0.5316	0.7291
No log	9.75	468	0.5353	0.6632	0.5353	0.7316
No log	9.7917	470	0.5353	0.6657	0.5353	0.7316
No log	9.8333	472	0.5349	0.6657	0.5349	0.7313
No log	9.875	474	0.5385	0.6614	0.5385	0.7338
No log	9.9167	476	0.5398	0.6614	0.5398	0.7347
No log	9.9583	478	0.5393	0.6614	0.5393	0.7343
No log	10.0	480	0.5390	0.6614	0.5390	0.7342

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1