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	4	5.5827	0.0322	5.5827	2.3628
No log	2.0	8	3.5144	0.0118	3.5144	1.8747
No log	3.0	12	2.5098	-0.0108	2.5098	1.5842
No log	4.0	16	1.8000	0.0420	1.8000	1.3417
No log	5.0	20	1.3377	0.0420	1.3377	1.1566
No log	6.0	24	1.0266	0.0316	1.0266	1.0132
No log	7.0	28	0.8910	0.0809	0.8910	0.9439
No log	8.0	32	0.7276	0.3282	0.7276	0.8530
No log	9.0	36	0.7118	0.3753	0.7118	0.8437
No log	10.0	40	0.7494	0.3518	0.7494	0.8657
No log	11.0	44	1.1830	0.2869	1.1830	1.0876
No log	12.0	48	0.7023	0.4884	0.7023	0.8380
No log	13.0	52	0.5586	0.5505	0.5586	0.7474
No log	14.0	56	0.8863	0.3387	0.8863	0.9414
No log	15.0	60	0.5800	0.4105	0.5800	0.7616
No log	16.0	64	0.8948	0.3079	0.8948	0.9460
No log	17.0	68	1.1005	0.3062	1.1005	1.0490
No log	18.0	72	0.6116	0.4953	0.6116	0.7820
No log	19.0	76	0.8929	0.3553	0.8929	0.9449
No log	20.0	80	0.5708	0.5009	0.5708	0.7555
No log	21.0	84	0.5746	0.5051	0.5746	0.7580
No log	22.0	88	0.6718	0.4828	0.6718	0.8197
No log	23.0	92	0.5996	0.5422	0.5996	0.7743
No log	24.0	96	0.5520	0.5809	0.5520	0.7430
No log	25.0	100	0.5455	0.5549	0.5455	0.7386
No log	26.0	104	0.8142	0.4470	0.8142	0.9023
No log	27.0	108	0.5799	0.5549	0.5799	0.7615
No log	28.0	112	0.8733	0.4482	0.8733	0.9345
No log	29.0	116	0.6122	0.5819	0.6122	0.7825
No log	30.0	120	0.8370	0.4891	0.8370	0.9149
No log	31.0	124	0.5185	0.5810	0.5185	0.7200
No log	32.0	128	1.5149	0.2843	1.5149	1.2308
No log	33.0	132	1.0959	0.3831	1.0959	1.0468
No log	34.0	136	0.7846	0.5206	0.7846	0.8858
No log	35.0	140	0.7679	0.4822	0.7679	0.8763
No log	36.0	144	0.7222	0.5218	0.7222	0.8498
No log	37.0	148	0.5604	0.5968	0.5604	0.7486
No log	38.0	152	0.9521	0.4433	0.9521	0.9758
No log	39.0	156	0.6954	0.5013	0.6954	0.8339
No log	40.0	160	0.5387	0.5904	0.5387	0.7339
No log	41.0	164	0.5636	0.5901	0.5636	0.7507
No log	42.0	168	0.6363	0.5474	0.6363	0.7977
No log	43.0	172	0.7394	0.4661	0.7394	0.8599
No log	44.0	176	0.5421	0.5889	0.5421	0.7363
No log	45.0	180	0.8209	0.4204	0.8209	0.9060
No log	46.0	184	0.5522	0.5860	0.5522	0.7431
No log	47.0	188	0.9569	0.3367	0.9569	0.9782
No log	48.0	192	0.6625	0.4940	0.6625	0.8140
No log	49.0	196	0.5832	0.5181	0.5832	0.7637
No log	50.0	200	0.7556	0.4316	0.7556	0.8692
No log	51.0	204	0.6191	0.5403	0.6191	0.7868
No log	52.0	208	0.6837	0.4829	0.6837	0.8269
No log	53.0	212	0.5909	0.5716	0.5909	0.7687
No log	54.0	216	0.7921	0.4426	0.7921	0.8900
No log	55.0	220	0.5855	0.5790	0.5855	0.7652
No log	56.0	224	0.7241	0.4820	0.7241	0.8509
No log	57.0	228	0.6253	0.5433	0.6253	0.7908
No log	58.0	232	0.5831	0.5817	0.5831	0.7636
No log	59.0	236	0.7388	0.4683	0.7388	0.8595
No log	60.0	240	0.5490	0.5527	0.5490	0.7409
No log	61.0	244	0.6271	0.5325	0.6271	0.7919
No log	62.0	248	0.5766	0.5721	0.5766	0.7594
No log	63.0	252	0.6313	0.5233	0.6313	0.7946
No log	64.0	256	0.5810	0.5578	0.5810	0.7623
No log	65.0	260	0.7444	0.4591	0.7444	0.8628
No log	66.0	264	0.5745	0.5589	0.5745	0.7580
No log	67.0	268	0.6425	0.5325	0.6425	0.8016

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold4

BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k5_k5_fold4