learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	14.8259	0.0	14.8234	3.8501
No log	2.0	2	12.5906	0.0	12.5880	3.5480
No log	3.0	3	11.2836	-0.0074	11.2808	3.3587
No log	4.0	4	10.9829	-0.0257	10.9802	3.3136
No log	5.0	5	10.5006	-0.0016	10.4979	3.2401
No log	6.0	6	9.8278	0.0	9.8250	3.1345
No log	7.0	7	8.9543	0.0	8.9515	2.9919
No log	8.0	8	7.9411	0.0	7.9384	2.8175
No log	9.0	9	7.1004	0.0	7.0981	2.6642
No log	10.0	10	6.6314	0.0	6.6291	2.5747
No log	11.0	11	6.3038	0.0	6.3016	2.5103
No log	12.0	12	5.8590	-0.0144	5.8569	2.4201
No log	13.0	13	5.6438	-0.0365	5.6415	2.3752
No log	14.0	14	4.8560	0.0108	4.8539	2.2032
No log	15.0	15	4.2157	0.0136	4.2139	2.0528
No log	16.0	16	3.7536	0.0025	3.7516	1.9369
No log	17.0	17	3.7670	0.0	3.7650	1.9404
No log	18.0	18	3.4250	0.0	3.4230	1.8501
No log	19.0	19	2.7086	0.0	2.7068	1.6452
No log	20.0	20	2.3134	0.0984	2.3117	1.5204
No log	21.0	21	2.0655	0.0958	2.0638	1.4366
No log	22.0	22	1.9726	0.0582	1.9709	1.4039
No log	23.0	23	1.8766	0.0573	1.8749	1.3693
No log	24.0	24	1.6319	0.0501	1.6303	1.2768
No log	25.0	25	1.4275	0.0467	1.4261	1.1942
No log	26.0	26	1.4038	0.0404	1.4023	1.1842
No log	27.0	27	1.3713	0.0467	1.3700	1.1704
No log	28.0	28	1.1770	0.0404	1.1758	1.0843
No log	29.0	29	1.0408	0.0404	1.0396	1.0196
No log	30.0	30	0.9266	0.0507	0.9255	0.9620
No log	31.0	31	0.9181	0.1416	0.9171	0.9576
No log	32.0	32	0.8327	0.3059	0.8318	0.9120
No log	33.0	33	0.8570	0.2765	0.8562	0.9253
No log	34.0	34	0.8089	0.3688	0.8080	0.8989
No log	35.0	35	0.8627	0.3092	0.8620	0.9284
No log	36.0	36	0.7581	0.4166	0.7574	0.8703
No log	37.0	37	0.8214	0.3660	0.8207	0.9059
No log	38.0	38	0.9670	0.2708	0.9663	0.9830
No log	39.0	39	0.8890	0.3072	0.8883	0.9425
No log	40.0	40	0.7363	0.4101	0.7356	0.8577
No log	41.0	41	0.7808	0.3645	0.7800	0.8832
No log	42.0	42	1.0079	0.2532	1.0071	1.0036
No log	43.0	43	1.0714	0.2460	1.0706	1.0347
No log	44.0	44	0.9097	0.2799	0.9088	0.9533
No log	45.0	45	0.9145	0.2794	0.9137	0.9559
No log	46.0	46	1.0711	0.2429	1.0702	1.0345
No log	47.0	47	1.0430	0.2476	1.0421	1.0208
No log	48.0	48	1.0437	0.2336	1.0428	1.0212
No log	49.0	49	1.0167	0.2418	1.0157	1.0078
No log	50.0	50	1.1360	0.1978	1.1349	1.0653
No log	51.0	51	1.4455	0.1270	1.4441	1.2017
No log	52.0	52	1.5192	0.1049	1.5178	1.2320
No log	53.0	53	1.3603	0.1476	1.3589	1.1657
No log	54.0	54	1.1546	0.2191	1.1534	1.0740
No log	55.0	55	1.1077	0.2287	1.1065	1.0519
No log	56.0	56	1.1094	0.2551	1.1081	1.0527
No log	57.0	57	1.2236	0.2126	1.2222	1.1055
No log	58.0	58	1.3282	0.1715	1.3268	1.1519
No log	59.0	59	1.2795	0.2006	1.2782	1.1306
No log	60.0	60	1.1461	0.2368	1.1448	1.0700
No log	61.0	61	1.1392	0.2529	1.1379	1.0667
No log	62.0	62	1.1839	0.2347	1.1826	1.0875
No log	63.0	63	1.2819	0.2056	1.2805	1.1316
No log	64.0	64	1.3515	0.1612	1.3500	1.1619
No log	65.0	65	1.3516	0.1640	1.3501	1.1619
No log	66.0	66	1.2771	0.2039	1.2757	1.1295

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex10_lo00_k1_k1_fold1

BERT_V8_sp10_lw40_ex10_lo00_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k1_k1_fold1