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	3	8.3457	0.0	8.3444	2.8887
No log	2.0	6	4.9259	0.0157	4.9248	2.2192
No log	3.0	9	3.5442	0.0	3.5431	1.8823
No log	4.0	12	2.4903	0.0345	2.4895	1.5778
No log	5.0	15	1.5301	0.0202	1.5295	1.2367
No log	6.0	18	1.2736	0.0	1.2730	1.1283
No log	7.0	21	0.9403	0.2454	0.9399	0.9695
No log	8.0	24	1.0451	0.0099	1.0446	1.0220
No log	9.0	27	0.8049	0.3939	0.8045	0.8969
No log	10.0	30	0.9118	0.1371	0.9113	0.9546
No log	11.0	33	0.7121	0.4241	0.7118	0.8437
No log	12.0	36	0.7002	0.4349	0.7000	0.8366
No log	13.0	39	0.8487	0.3230	0.8485	0.9212
No log	14.0	42	0.5878	0.5215	0.5878	0.7667
No log	15.0	45	0.7191	0.4976	0.7190	0.8479
No log	16.0	48	0.5168	0.5093	0.5171	0.7191
No log	17.0	51	0.5160	0.5781	0.5165	0.7186
No log	18.0	54	0.5281	0.5386	0.5287	0.7271
No log	19.0	57	0.5097	0.6298	0.5102	0.7143
No log	20.0	60	0.5887	0.6297	0.5893	0.7677
No log	21.0	63	0.5667	0.6042	0.5672	0.7531
No log	22.0	66	0.5360	0.5990	0.5366	0.7325
No log	23.0	69	0.5606	0.6152	0.5612	0.7491
No log	24.0	72	0.5921	0.6040	0.5923	0.7696
No log	25.0	75	0.5421	0.6187	0.5425	0.7366
No log	26.0	78	0.6410	0.5348	0.6409	0.8006
No log	27.0	81	0.5305	0.5969	0.5308	0.7286
No log	28.0	84	0.5269	0.5700	0.5271	0.7260
No log	29.0	87	0.5339	0.5964	0.5342	0.7309
No log	30.0	90	0.5622	0.5657	0.5623	0.7498
No log	31.0	93	0.5646	0.5744	0.5649	0.7516
No log	32.0	96	0.6082	0.5578	0.6081	0.7798
No log	33.0	99	0.5270	0.5977	0.5272	0.7261
No log	34.0	102	0.5813	0.5865	0.5813	0.7624
No log	35.0	105	0.5839	0.5751	0.5842	0.7643
No log	36.0	108	0.7005	0.5104	0.7005	0.8369
No log	37.0	111	0.6718	0.5141	0.6719	0.8197
No log	38.0	114	0.8479	0.5183	0.8485	0.9211
No log	39.0	117	0.6595	0.5615	0.6600	0.8124
No log	40.0	120	0.6797	0.5105	0.6798	0.8245
No log	41.0	123	0.5802	0.5715	0.5803	0.7618
No log	42.0	126	0.6116	0.5767	0.6121	0.7824
No log	43.0	129	0.5276	0.6203	0.5279	0.7266
No log	44.0	132	0.6343	0.5740	0.6344	0.7965
No log	45.0	135	0.5301	0.6091	0.5303	0.7282
No log	46.0	138	0.5441	0.5957	0.5444	0.7378
No log	47.0	141	0.5714	0.5656	0.5715	0.7560
No log	48.0	144	0.5789	0.5772	0.5792	0.7610
No log	49.0	147	0.5740	0.5609	0.5743	0.7578

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_k3_k3_fold3

BERT_V8_sp10_lw40_ex10_lo00_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex10_lo00_k3_k3_fold3