ASAP_FineTuningBERT_AugV7_k1_task1_organization_fold2

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: 0.7115
• Qwk: 0.4547
• Mse: 0.7119
• Rmse: 0.8438

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	11.8613	-0.0253	11.8608	3.4440
No log	2.0	4	9.6891	-0.0005	9.6888	3.1127
No log	3.0	6	7.8126	0.0	7.8122	2.7950
No log	4.0	8	6.3258	0.0	6.3255	2.5151
7.835	5.0	10	5.0433	0.0102	5.0431	2.2457
7.835	6.0	12	3.9672	0.0	3.9670	1.9917
7.835	7.0	14	3.2940	0.0	3.2939	1.8149
7.835	8.0	16	2.4571	0.0949	2.4570	1.5675
7.835	9.0	18	1.9262	0.0213	1.9262	1.3879
3.3945	10.0	20	1.5645	0.0107	1.5646	1.2509
3.3945	11.0	22	1.3252	0.0	1.3253	1.1512
3.3945	12.0	24	1.2344	0.0107	1.2345	1.1111
3.3945	13.0	26	1.0751	0.0174	1.0752	1.0369
3.3945	14.0	28	0.9193	0.0174	0.9195	0.9589
1.7632	15.0	30	1.0231	0.0602	1.0233	1.0116
1.7632	16.0	32	1.1071	0.1027	1.1074	1.0523
1.7632	17.0	34	0.7933	0.3564	0.7936	0.8908
1.7632	18.0	36	0.7031	0.4863	0.7034	0.8387
1.7632	19.0	38	0.7888	0.4038	0.7891	0.8883
1.7278	20.0	40	0.6392	0.4365	0.6395	0.7997
1.7278	21.0	42	0.6253	0.3499	0.6256	0.7910
1.7278	22.0	44	0.6477	0.3630	0.6481	0.8050
1.7278	23.0	46	0.6454	0.3451	0.6458	0.8036
1.7278	24.0	48	0.6425	0.3840	0.6427	0.8017
0.8864	25.0	50	0.6544	0.3261	0.6548	0.8092
0.8864	26.0	52	0.6420	0.4107	0.6422	0.8014
0.8864	27.0	54	0.7261	0.3847	0.7261	0.8521
0.8864	28.0	56	0.7674	0.3683	0.7675	0.8761
0.8864	29.0	58	0.7889	0.3829	0.7892	0.8884
0.3932	30.0	60	0.8059	0.3561	0.8060	0.8977
0.3932	31.0	62	0.7281	0.3566	0.7283	0.8534
0.3932	32.0	64	0.7054	0.4396	0.7057	0.8401
0.3932	33.0	66	0.7036	0.4377	0.7039	0.8390
0.3932	34.0	68	0.7848	0.3864	0.7849	0.8860
0.2445	35.0	70	0.7649	0.4139	0.7652	0.8748
0.2445	36.0	72	1.0594	0.3780	1.0600	1.0296
0.2445	37.0	74	1.0914	0.3646	1.0920	1.0450
0.2445	38.0	76	0.8118	0.4242	0.8122	0.9012
0.2445	39.0	78	0.7972	0.3886	0.7973	0.8929
0.2043	40.0	80	0.7441	0.4158	0.7444	0.8628
0.2043	41.0	82	0.7677	0.4002	0.7681	0.8764
0.2043	42.0	84	0.7478	0.4004	0.7482	0.8650
0.2043	43.0	86	0.7508	0.4173	0.7511	0.8667
0.2043	44.0	88	0.9182	0.4479	0.9186	0.9584
0.1376	45.0	90	0.9471	0.4305	0.9475	0.9734
0.1376	46.0	92	0.8571	0.3622	0.8573	0.9259
0.1376	47.0	94	0.8765	0.3366	0.8767	0.9363
0.1376	48.0	96	0.9869	0.3437	0.9874	0.9937
0.1376	49.0	98	0.9751	0.3608	0.9756	0.9877
0.1317	50.0	100	0.7735	0.4120	0.7739	0.8797
0.1317	51.0	102	0.7438	0.3984	0.7442	0.8626
0.1317	52.0	104	0.7046	0.4521	0.7049	0.8396
0.1317	53.0	106	0.7440	0.4640	0.7445	0.8629
0.1317	54.0	108	0.8412	0.4499	0.8417	0.9175
0.1104	55.0	110	0.7857	0.4605	0.7862	0.8867
0.1104	56.0	112	0.7506	0.4489	0.7511	0.8666
0.1104	57.0	114	0.7514	0.4526	0.7519	0.8671
0.1104	58.0	116	0.7316	0.4580	0.7321	0.8556
0.1104	59.0	118	0.6595	0.5134	0.6600	0.8124
0.0744	60.0	120	0.6575	0.5058	0.6580	0.8112
0.0744	61.0	122	0.6696	0.4840	0.6701	0.8186
0.0744	62.0	124	0.7853	0.4539	0.7858	0.8865
0.0744	63.0	126	0.8456	0.4284	0.8461	0.9198
0.0744	64.0	128	0.7764	0.4004	0.7768	0.8814
0.1048	65.0	130	0.7731	0.3792	0.7734	0.8794
0.1048	66.0	132	0.7557	0.3958	0.7560	0.8695
0.1048	67.0	134	0.7364	0.4323	0.7367	0.8583
0.1048	68.0	136	0.8066	0.4360	0.8070	0.8983
0.1048	69.0	138	0.7773	0.4461	0.7777	0.8819
0.0972	70.0	140	0.6925	0.4961	0.6929	0.8324
0.0972	71.0	142	0.6561	0.5029	0.6565	0.8102
0.0972	72.0	144	0.6562	0.5194	0.6566	0.8103
0.0972	73.0	146	0.6604	0.5002	0.6608	0.8129
0.0972	74.0	148	0.7327	0.4786	0.7332	0.8563
0.0736	75.0	150	0.7795	0.4670	0.7800	0.8832
0.0736	76.0	152	0.7596	0.4570	0.7601	0.8718
0.0736	77.0	154	0.7092	0.4808	0.7096	0.8424
0.0736	78.0	156	0.6812	0.4770	0.6816	0.8256
0.0736	79.0	158	0.6716	0.4847	0.6720	0.8198
0.0564	80.0	160	0.6754	0.4880	0.6759	0.8221
0.0564	81.0	162	0.7156	0.4797	0.7160	0.8462
0.0564	82.0	164	0.7282	0.4692	0.7286	0.8536
0.0564	83.0	166	0.7243	0.4650	0.7248	0.8513
0.0564	84.0	168	0.7013	0.4721	0.7018	0.8377
0.0461	85.0	170	0.7083	0.4820	0.7087	0.8419
0.0461	86.0	172	0.7360	0.4707	0.7365	0.8582
0.0461	87.0	174	0.7468	0.4713	0.7473	0.8645
0.0461	88.0	176	0.7544	0.4744	0.7549	0.8688
0.0461	89.0	178	0.7454	0.4698	0.7459	0.8636
0.0514	90.0	180	0.7113	0.4618	0.7117	0.8436
0.0514	91.0	182	0.6902	0.4754	0.6907	0.8311
0.0514	92.0	184	0.6777	0.4812	0.6781	0.8235
0.0514	93.0	186	0.6726	0.4836	0.6730	0.8204
0.0514	94.0	188	0.6770	0.4802	0.6775	0.8231
0.0542	95.0	190	0.6886	0.4833	0.6890	0.8301
0.0542	96.0	192	0.6992	0.4711	0.6996	0.8364
0.0542	97.0	194	0.7039	0.4704	0.7044	0.8393
0.0542	98.0	196	0.7086	0.4615	0.7090	0.8420
0.0542	99.0	198	0.7118	0.4540	0.7122	0.8439
0.0404	100.0	200	0.7115	0.4547	0.7119	0.8438

Framework versions

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