learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	1	10.5093	0.0019	10.5068	3.2414
No log	2.0	2	8.7850	-0.0002	8.7827	2.9636
No log	3.0	3	7.4729	0.0	7.4704	2.7332
No log	4.0	4	6.6926	0.0	6.6903	2.5866
No log	5.0	5	6.2097	0.0	6.2073	2.4915
No log	6.0	6	5.7641	-0.0163	5.7618	2.4004
No log	7.0	7	5.2908	0.0	5.2886	2.2997
No log	8.0	8	4.7875	0.0	4.7854	2.1875
No log	9.0	9	4.2763	0.0	4.2742	2.0674
No log	10.0	10	3.7906	0.0	3.7886	1.9464
No log	11.0	11	3.3626	0.0	3.3607	1.8332
No log	12.0	12	2.9991	0.0	2.9972	1.7313
No log	13.0	13	2.6946	0.0	2.6927	1.6410
No log	14.0	14	2.4434	-0.0012	2.4416	1.5626
No log	15.0	15	2.1879	0.1162	2.1862	1.4786
No log	16.0	16	1.9276	0.0583	1.9260	1.3878
No log	17.0	17	1.7158	0.0583	1.7143	1.3093
No log	18.0	18	1.5506	0.0211	1.5490	1.2446
No log	19.0	19	1.4256	0.0106	1.4240	1.1933
No log	20.0	20	1.2689	0.0106	1.2675	1.1258
No log	21.0	21	1.1662	0.0	1.1648	1.0793
No log	22.0	22	1.0785	0.0	1.0771	1.0378
No log	23.0	23	1.0046	0.0	1.0033	1.0016
No log	24.0	24	0.9398	0.0106	0.9385	0.9687
No log	25.0	25	0.8693	0.0446	0.8680	0.9317
No log	26.0	26	0.8499	0.2716	0.8487	0.9213
No log	27.0	27	0.7810	0.3763	0.7798	0.8831
No log	28.0	28	0.7333	0.3780	0.7322	0.8557
No log	29.0	29	0.6833	0.4068	0.6822	0.8259
No log	30.0	30	0.6952	0.3717	0.6941	0.8331
No log	31.0	31	0.6174	0.4308	0.6164	0.7851
No log	32.0	32	0.5769	0.4692	0.5758	0.7588
No log	33.0	33	0.5411	0.4999	0.5401	0.7349
No log	34.0	34	0.5740	0.4775	0.5730	0.7570
No log	35.0	35	0.5032	0.5439	0.5022	0.7087
No log	36.0	36	0.6180	0.4589	0.6170	0.7855
No log	37.0	37	0.5604	0.5040	0.5594	0.7479
No log	38.0	38	0.4635	0.6033	0.4626	0.6801
No log	39.0	39	0.4871	0.5669	0.4862	0.6973
No log	40.0	40	0.7304	0.4496	0.7294	0.8540
No log	41.0	41	0.7296	0.4523	0.7287	0.8536
No log	42.0	42	0.5380	0.5782	0.5372	0.7329
No log	43.0	43	0.4575	0.6606	0.4567	0.6758
No log	44.0	44	0.4901	0.6690	0.4893	0.6995
No log	45.0	45	0.7225	0.5092	0.7216	0.8495
No log	46.0	46	0.8038	0.4903	0.8029	0.8960
No log	47.0	47	0.6801	0.5849	0.6793	0.8242
No log	48.0	48	0.5812	0.6546	0.5805	0.7619
No log	49.0	49	0.6052	0.6366	0.6045	0.7775
No log	50.0	50	0.8076	0.5566	0.8069	0.8982
No log	51.0	51	0.8324	0.5429	0.8317	0.9119
No log	52.0	52	0.7288	0.5852	0.7280	0.8533
No log	53.0	53	0.6536	0.6139	0.6529	0.8080
No log	54.0	54	0.7707	0.5855	0.7700	0.8775
No log	55.0	55	0.8997	0.5501	0.8990	0.9481
No log	56.0	56	0.9499	0.5396	0.9491	0.9742
No log	57.0	57	0.7617	0.6062	0.7610	0.8724
No log	58.0	58	0.8151	0.5932	0.8144	0.9025
No log	59.0	59	0.8758	0.5845	0.8751	0.9355
No log	60.0	60	0.7737	0.6195	0.7730	0.8792
No log	61.0	61	0.8975	0.5821	0.8968	0.9470
No log	62.0	62	1.0986	0.5148	1.0979	1.0478
No log	63.0	63	1.0484	0.5390	1.0476	1.0235
No log	64.0	64	0.8622	0.6082	0.8615	0.9282

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold1

Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold1