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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	12.6506	0.0	12.6506	3.5568
No log	2.0	4	11.9458	0.0	11.9458	3.4563
No log	3.0	6	11.3317	-0.0166	11.3317	3.3663
No log	4.0	8	10.3366	0.0018	10.3366	3.2151
No log	5.0	10	8.7699	0.0	8.7699	2.9614
No log	6.0	12	7.8696	0.0	7.8696	2.8053
No log	7.0	14	6.4719	0.0	6.4719	2.5440
No log	8.0	16	5.5514	0.0263	5.5514	2.3561
No log	9.0	18	4.8133	0.0118	4.8133	2.1939
No log	10.0	20	4.1095	0.0079	4.1095	2.0272
No log	11.0	22	3.3913	0.0079	3.3913	1.8415
No log	12.0	24	2.8632	0.0040	2.8632	1.6921
No log	13.0	26	2.4135	0.0051	2.4135	1.5535
No log	14.0	28	1.9631	0.0493	1.9631	1.4011
No log	15.0	30	1.7013	0.0470	1.7013	1.3044
No log	16.0	32	1.5252	0.0344	1.5252	1.2350
No log	17.0	34	1.4107	0.0445	1.4107	1.1877
No log	18.0	36	1.1215	0.0344	1.1215	1.0590
No log	19.0	38	1.1769	0.0213	1.1769	1.0848
No log	20.0	40	0.8195	0.3021	0.8195	0.9052
No log	21.0	42	0.6956	0.4476	0.6956	0.8340
No log	22.0	44	0.6169	0.4091	0.6169	0.7854
No log	23.0	46	0.6926	0.4634	0.6926	0.8322
No log	24.0	48	0.7935	0.4667	0.7935	0.8908
No log	25.0	50	0.7155	0.5005	0.7155	0.8458
No log	26.0	52	0.6352	0.5357	0.6352	0.7970
No log	27.0	54	1.0582	0.3988	1.0582	1.0287
No log	28.0	56	1.0037	0.4487	1.0037	1.0018
No log	29.0	58	0.6800	0.5436	0.6800	0.8246
No log	30.0	60	0.6922	0.5359	0.6922	0.8320
No log	31.0	62	0.8560	0.5246	0.8560	0.9252
No log	32.0	64	0.7553	0.5641	0.7553	0.8691
No log	33.0	66	0.7246	0.5831	0.7246	0.8512
No log	34.0	68	0.7860	0.5793	0.7860	0.8866
No log	35.0	70	0.7902	0.5937	0.7902	0.8889
No log	36.0	72	0.7535	0.5910	0.7535	0.8680
No log	37.0	74	0.8952	0.5303	0.8952	0.9462
No log	38.0	76	0.9010	0.5265	0.9010	0.9492
No log	39.0	78	0.8201	0.5781	0.8201	0.9056
No log	40.0	80	0.9928	0.5230	0.9928	0.9964
No log	41.0	82	0.8497	0.5890	0.8497	0.9218
No log	42.0	84	1.0559	0.4607	1.0559	1.0276
No log	43.0	86	0.9336	0.4684	0.9336	0.9662
No log	44.0	88	0.6703	0.5763	0.6703	0.8187
No log	45.0	90	0.7841	0.5532	0.7841	0.8855
No log	46.0	92	0.8311	0.5464	0.8311	0.9116
No log	47.0	94	0.6247	0.6338	0.6247	0.7904
No log	48.0	96	0.7086	0.5625	0.7086	0.8418
No log	49.0	98	0.7256	0.5886	0.7256	0.8518
No log	50.0	100	0.7735	0.5884	0.7735	0.8795
No log	51.0	102	1.0987	0.5207	1.0987	1.0482
No log	52.0	104	1.2016	0.4869	1.2016	1.0962
No log	53.0	106	0.8303	0.5430	0.8303	0.9112
No log	54.0	108	0.9790	0.4346	0.9790	0.9894
No log	55.0	110	1.2693	0.3434	1.2693	1.1266
No log	56.0	112	0.8942	0.4531	0.8942	0.9456
No log	57.0	114	0.6650	0.5711	0.6650	0.8155
No log	58.0	116	0.8054	0.5652	0.8054	0.8974
No log	59.0	118	0.7959	0.5856	0.7959	0.8921
No log	60.0	120	0.8211	0.5735	0.8211	0.9061
No log	61.0	122	0.8631	0.5699	0.8631	0.9290
No log	62.0	124	0.8231	0.5681	0.8231	0.9073

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_AugV8_k1_task1_organization_sp020_lw010_fold4

BERT_AugV8_k1_task1_organization_sp020_lw010_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp020_lw010_fold4