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	2	11.0917	0.0163	11.0918	3.3304
No log	2.0	4	9.9428	0.0	9.9431	3.1533
No log	3.0	6	8.9046	0.0	8.9049	2.9841
No log	4.0	8	7.9759	0.0	7.9762	2.8242
No log	5.0	10	6.9082	0.0	6.9085	2.6284
No log	6.0	12	5.6194	0.0421	5.6197	2.3706
No log	7.0	14	4.6577	0.0066	4.6580	2.1583
No log	8.0	16	3.6325	0.0	3.6328	1.9060
No log	9.0	18	2.6746	0.0148	2.6750	1.6356
No log	10.0	20	2.1273	0.0923	2.1277	1.4587
No log	11.0	22	2.0010	0.0492	2.0015	1.4147
No log	12.0	24	1.3750	0.0213	1.3755	1.1728
No log	13.0	26	1.1152	0.0213	1.1157	1.0563
No log	14.0	28	1.0814	0.0107	1.0818	1.0401
No log	15.0	30	1.0075	0.0508	1.0079	1.0040
No log	16.0	32	0.8020	0.2767	0.8024	0.8958
No log	17.0	34	0.7703	0.3014	0.7706	0.8778
No log	18.0	36	0.7697	0.3840	0.7700	0.8775
No log	19.0	38	0.7394	0.3688	0.7396	0.8600
No log	20.0	40	0.6898	0.2888	0.6900	0.8307
No log	21.0	42	0.7581	0.2116	0.7582	0.8707
No log	22.0	44	0.7610	0.1867	0.7610	0.8724
No log	23.0	46	0.7898	0.2032	0.7898	0.8887
No log	24.0	48	0.7123	0.3734	0.7123	0.8440
No log	25.0	50	0.8260	0.3543	0.8261	0.9089
No log	26.0	52	0.9662	0.3185	0.9663	0.9830
No log	27.0	54	0.9734	0.3082	0.9735	0.9867
No log	28.0	56	0.7677	0.3619	0.7678	0.8762
No log	29.0	58	0.8661	0.2051	0.8661	0.9307
No log	30.0	60	1.1275	0.0580	1.1276	1.0619
No log	31.0	62	0.9697	0.1658	0.9698	0.9848
No log	32.0	64	0.7679	0.3121	0.7680	0.8763
No log	33.0	66	0.8191	0.2520	0.8190	0.9050
No log	34.0	68	0.8839	0.2072	0.8839	0.9401
No log	35.0	70	0.6679	0.4055	0.6679	0.8172
No log	36.0	72	0.6606	0.4398	0.6605	0.8127
No log	37.0	74	0.9276	0.2159	0.9275	0.9631
No log	38.0	76	1.0832	0.1397	1.0830	1.0407
No log	39.0	78	0.8696	0.2633	0.8694	0.9324
No log	40.0	80	0.7550	0.3108	0.7549	0.8689
No log	41.0	82	0.7985	0.2966	0.7984	0.8935
No log	42.0	84	1.1578	0.0434	1.1577	1.0760
No log	43.0	86	1.2502	-0.0040	1.2502	1.1181
No log	44.0	88	0.8935	0.2003	0.8935	0.9452
No log	45.0	90	0.7347	0.4127	0.7347	0.8571
No log	46.0	92	0.7531	0.3551	0.7530	0.8678
No log	47.0	94	1.0956	0.0819	1.0958	1.0468
No log	48.0	96	1.3487	0.0002	1.3490	1.1615
No log	49.0	98	1.2344	0.0822	1.2346	1.1111
No log	50.0	100	0.8901	0.2600	0.8901	0.9434
No log	51.0	102	0.6372	0.4570	0.6371	0.7982
No log	52.0	104	0.5924	0.5292	0.5922	0.7695
No log	53.0	106	0.6312	0.5085	0.6310	0.7943
No log	54.0	108	0.8508	0.2775	0.8508	0.9224
No log	55.0	110	1.1955	0.0491	1.1956	1.0935
No log	56.0	112	1.1246	0.0991	1.1248	1.0605
No log	57.0	114	0.7953	0.3982	0.7954	0.8918
No log	58.0	116	0.7192	0.4609	0.7191	0.8480
No log	59.0	118	0.7257	0.4258	0.7256	0.8518
No log	60.0	120	0.9509	0.1850	0.9509	0.9752
No log	61.0	122	1.1314	0.0679	1.1316	1.0637
No log	62.0	124	1.1996	0.0699	1.1998	1.0954
No log	63.0	126	1.0655	0.0986	1.0657	1.0323
No log	64.0	128	0.8173	0.2411	0.8174	0.9041
No log	65.0	130	0.6577	0.4059	0.6575	0.8109
No log	66.0	132	0.6401	0.4326	0.6399	0.7999
No log	67.0	134	0.6955	0.3883	0.6954	0.8339
No log	68.0	136	0.8346	0.2541	0.8347	0.9136
No log	69.0	138	1.0761	0.0620	1.0764	1.0375
No log	70.0	140	1.1344	0.0544	1.1346	1.0652
No log	71.0	142	0.9824	0.1304	0.9825	0.9912
No log	72.0	144	0.7553	0.3705	0.7552	0.8690
No log	73.0	146	0.6453	0.4772	0.6450	0.8031
No log	74.0	148	0.6069	0.5108	0.6066	0.7788
No log	75.0	150	0.6283	0.4708	0.6280	0.7925
No log	76.0	152	0.6936	0.3993	0.6935	0.8327
No log	77.0	154	0.7855	0.3161	0.7855	0.8863
No log	78.0	156	0.8420	0.2830	0.8421	0.9176
No log	79.0	158	0.8718	0.2532	0.8719	0.9337
No log	80.0	160	0.8410	0.2824	0.8410	0.9171
No log	81.0	162	0.7930	0.3253	0.7930	0.8905
No log	82.0	164	0.8012	0.3460	0.8011	0.8950

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold2

BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold2