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	3	11.3496	0.0018	11.3473	3.3686
No log	2.0	6	9.1141	-0.0003	9.1129	3.0188
No log	3.0	9	7.3182	0.0	7.3167	2.7049
No log	4.0	12	5.8638	0.0459	5.8624	2.4212
No log	5.0	15	4.5881	0.0114	4.5869	2.1417
No log	6.0	18	3.6355	0.0	3.6344	1.9064
No log	7.0	21	2.8694	0.0	2.8685	1.6937
No log	8.0	24	2.2312	0.0729	2.2304	1.4934
No log	9.0	27	1.6728	0.0365	1.6721	1.2931
No log	10.0	30	1.3567	0.0102	1.3560	1.1645
No log	11.0	33	1.0428	0.0365	1.0423	1.0209
No log	12.0	36	0.8723	0.3226	0.8718	0.9337
No log	13.0	39	0.7883	0.4249	0.7880	0.8877
No log	14.0	42	1.1554	0.1847	1.1553	1.0749
No log	15.0	45	0.7845	0.4770	0.7843	0.8856
No log	16.0	48	0.7336	0.5137	0.7334	0.8564
No log	17.0	51	1.2565	0.2519	1.2566	1.1210
No log	18.0	54	0.8985	0.4046	0.8985	0.9479
No log	19.0	57	0.7824	0.4472	0.7824	0.8845
No log	20.0	60	0.5798	0.5807	0.5801	0.7617
No log	21.0	63	0.5172	0.5597	0.5177	0.7195
No log	22.0	66	0.5183	0.5613	0.5188	0.7203
No log	23.0	69	0.5288	0.5852	0.5292	0.7275
No log	24.0	72	0.5578	0.6059	0.5582	0.7471
No log	25.0	75	0.5970	0.5747	0.5976	0.7731
No log	26.0	78	0.5502	0.5845	0.5506	0.7421
No log	27.0	81	0.7264	0.4982	0.7267	0.8525
No log	28.0	84	0.5535	0.6156	0.5542	0.7444
No log	29.0	87	0.6570	0.5265	0.6574	0.8108
No log	30.0	90	0.6410	0.5270	0.6414	0.8008
No log	31.0	93	0.6149	0.5533	0.6153	0.7844
No log	32.0	96	0.7919	0.4933	0.7919	0.8899
No log	33.0	99	0.6294	0.6043	0.6298	0.7936
No log	34.0	102	0.7576	0.5190	0.7576	0.8704
No log	35.0	105	0.5995	0.6333	0.5998	0.7745
No log	36.0	108	0.9643	0.4582	0.9642	0.9820
No log	37.0	111	0.6776	0.5650	0.6779	0.8234
No log	38.0	114	0.8036	0.5209	0.8045	0.8969
No log	39.0	117	0.7782	0.4919	0.7782	0.8822
No log	40.0	120	0.6478	0.5418	0.6478	0.8049
No log	41.0	123	0.7233	0.4921	0.7232	0.8504
No log	42.0	126	0.5929	0.5761	0.5932	0.7702
No log	43.0	129	0.6682	0.5316	0.6684	0.8176
No log	44.0	132	0.6009	0.6087	0.6014	0.7755
No log	45.0	135	0.6836	0.5460	0.6838	0.8269
No log	46.0	138	0.8012	0.4922	0.8012	0.8951
No log	47.0	141	0.5829	0.5972	0.5833	0.7637
No log	48.0	144	0.7132	0.5065	0.7132	0.8445
No log	49.0	147	0.6236	0.5722	0.6238	0.7898
No log	50.0	150	0.6132	0.5526	0.6135	0.7833
No log	51.0	153	0.6268	0.5561	0.6270	0.7918
No log	52.0	156	0.6491	0.5495	0.6493	0.8058
No log	53.0	159	0.6118	0.5512	0.6121	0.7824
No log	54.0	162	0.6451	0.5512	0.6453	0.8033
No log	55.0	165	0.6638	0.5444	0.6639	0.8148
No log	56.0	168	0.6043	0.5793	0.6045	0.7775
No log	57.0	171	0.8840	0.4582	0.8838	0.9401
No log	58.0	174	0.6686	0.5374	0.6686	0.8177
No log	59.0	177	0.5847	0.5947	0.5849	0.7648
No log	60.0	180	0.7548	0.4954	0.7547	0.8688
No log	61.0	183	0.6696	0.5358	0.6696	0.8183
No log	62.0	186	0.5823	0.6001	0.5825	0.7632
No log	63.0	189	0.7350	0.5090	0.7350	0.8573
No log	64.0	192	0.6620	0.5279	0.6621	0.8137
No log	65.0	195	0.6173	0.5577	0.6174	0.7858

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_k3_k3_fold3

BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k3_k3_fold3