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	11.4227	0.0145	11.4225	3.3797
No log	2.0	2	9.7662	0.0046	9.7661	3.1251
No log	3.0	3	8.4371	0.0	8.4372	2.9047
No log	4.0	4	7.1765	0.0	7.1766	2.6789
No log	5.0	5	6.0750	0.0542	6.0753	2.4648
No log	6.0	6	5.4454	0.0614	5.4457	2.3336
No log	7.0	7	4.9287	0.0335	4.9290	2.2201
No log	8.0	8	4.3551	0.0117	4.3554	2.0870
No log	9.0	9	3.8188	0.0155	3.8192	1.9543
No log	10.0	10	3.3818	0.0078	3.3820	1.8390
No log	11.0	11	2.9321	0.0	2.9324	1.7124
No log	12.0	12	2.5771	0.0022	2.5774	1.6054
No log	13.0	13	2.2853	0.1718	2.2856	1.5118
No log	14.0	14	2.0194	0.0810	2.0198	1.4212
No log	15.0	15	1.7836	0.0577	1.7839	1.3356
No log	16.0	16	1.5680	0.0501	1.5683	1.2523
No log	17.0	17	1.3995	0.0449	1.3999	1.1832
No log	18.0	18	1.2434	0.0213	1.2437	1.1152
No log	19.0	19	1.1554	0.0213	1.1558	1.0751
No log	20.0	20	1.0525	0.0	1.0529	1.0261
No log	21.0	21	0.9401	0.0	0.9405	0.9698
No log	22.0	22	0.8762	0.0993	0.8765	0.9362
No log	23.0	23	0.8002	0.3633	0.8006	0.8947
No log	24.0	24	0.7551	0.4025	0.7554	0.8691
No log	25.0	25	0.7321	0.3950	0.7324	0.8558
No log	26.0	26	0.7034	0.3977	0.7037	0.8388
No log	27.0	27	0.6397	0.3870	0.6399	0.8000
No log	28.0	28	0.6041	0.3835	0.6042	0.7773
No log	29.0	29	0.5458	0.4467	0.5459	0.7389
No log	30.0	30	0.5114	0.4653	0.5114	0.7152
No log	31.0	31	0.5303	0.4607	0.5303	0.7282
No log	32.0	32	0.5280	0.4593	0.5279	0.7266
No log	33.0	33	0.4727	0.5124	0.4727	0.6875
No log	34.0	34	0.4594	0.5346	0.4594	0.6778
No log	35.0	35	0.4862	0.5086	0.4861	0.6972
No log	36.0	36	0.5250	0.4875	0.5249	0.7245
No log	37.0	37	0.4941	0.5763	0.4941	0.7029
No log	38.0	38	0.4512	0.5686	0.4513	0.6718
No log	39.0	39	0.4596	0.5405	0.4597	0.6780
No log	40.0	40	0.4488	0.5590	0.4488	0.6699
No log	41.0	41	0.5439	0.5670	0.5438	0.7374
No log	42.0	42	0.5785	0.5650	0.5784	0.7605
No log	43.0	43	0.5173	0.5901	0.5172	0.7192
No log	44.0	44	0.4487	0.5904	0.4488	0.6699
No log	45.0	45	0.4645	0.5968	0.4647	0.6817
No log	46.0	46	0.4646	0.6134	0.4647	0.6817
No log	47.0	47	0.4656	0.6122	0.4656	0.6824
No log	48.0	48	0.5378	0.6096	0.5377	0.7333
No log	49.0	49	0.5491	0.5999	0.5490	0.7410
No log	50.0	50	0.4900	0.6264	0.4900	0.7000
No log	51.0	51	0.4616	0.6391	0.4618	0.6795
No log	52.0	52	0.4636	0.6187	0.4637	0.6810
No log	53.0	53	0.4609	0.6146	0.4610	0.6790
No log	54.0	54	0.5164	0.6032	0.5165	0.7187
No log	55.0	55	0.5454	0.5865	0.5454	0.7385
No log	56.0	56	0.5080	0.6010	0.5081	0.7128
No log	57.0	57	0.4661	0.6140	0.4663	0.6829
No log	58.0	58	0.4648	0.6139	0.4650	0.6819
No log	59.0	59	0.4750	0.6106	0.4751	0.6893
No log	60.0	60	0.5080	0.6095	0.5081	0.7128
No log	61.0	61	0.5262	0.6003	0.5264	0.7255
No log	62.0	62	0.5036	0.6099	0.5037	0.7097
No log	63.0	63	0.4873	0.6247	0.4874	0.6982
No log	64.0	64	0.5004	0.6157	0.5006	0.7075
No log	65.0	65	0.5431	0.5837	0.5432	0.7370
No log	66.0	66	0.5401	0.5837	0.5403	0.7350
No log	67.0	67	0.5064	0.6120	0.5066	0.7118
No log	68.0	68	0.5100	0.6092	0.5101	0.7142
No log	69.0	69	0.5459	0.5823	0.5460	0.7389
No log	70.0	70	0.5460	0.5827	0.5461	0.7390
No log	71.0	71	0.5188	0.6007	0.5189	0.7204
No log	72.0	72	0.5244	0.5958	0.5246	0.7243
No log	73.0	73	0.5422	0.5926	0.5424	0.7365
No log	74.0	74	0.5809	0.5691	0.5811	0.7623
No log	75.0	75	0.5712	0.5716	0.5713	0.7558
No log	76.0	76	0.5288	0.5937	0.5290	0.7273
No log	77.0	77	0.5298	0.5944	0.5300	0.7280
No log	78.0	78	0.5634	0.5761	0.5635	0.7507
No log	79.0	79	0.5594	0.5790	0.5595	0.7480
No log	80.0	80	0.5589	0.5775	0.5591	0.7477
No log	81.0	81	0.5301	0.5929	0.5303	0.7282

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold2

BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k1_k1_fold2