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	10.0483	0.0036	10.0483	3.1699
No log	2.0	2	8.9108	0.0	8.9108	2.9851
No log	3.0	3	8.0625	0.0	8.0625	2.8394
No log	4.0	4	7.5347	0.0	7.5347	2.7449
No log	5.0	5	7.0416	0.0	7.0416	2.6536
No log	6.0	6	6.6422	0.0	6.6422	2.5773
No log	7.0	7	6.2135	-0.0007	6.2135	2.4927
No log	8.0	8	5.7842	0.0173	5.7842	2.4050
No log	9.0	9	5.3573	0.0112	5.3573	2.3146
No log	10.0	10	4.9228	0.0115	4.9228	2.2187
No log	11.0	11	4.4961	0.0115	4.4961	2.1204
No log	12.0	12	4.0843	0.0039	4.0843	2.0210
No log	13.0	13	3.6744	0.0039	3.6744	1.9169
No log	14.0	14	3.2588	0.0	3.2588	1.8052
No log	15.0	15	2.8628	0.0	2.8628	1.6920
No log	16.0	16	2.5200	0.0880	2.5200	1.5875
No log	17.0	17	2.2179	0.0850	2.2179	1.4893
No log	18.0	18	1.9581	0.0511	1.9581	1.3993
No log	19.0	19	1.7607	0.0409	1.7607	1.3269
No log	20.0	20	1.5954	0.0316	1.5954	1.2631
No log	21.0	21	1.4326	0.0316	1.4326	1.1969
No log	22.0	22	1.2948	0.0316	1.2948	1.1379
No log	23.0	23	1.1614	0.0316	1.1614	1.0777
No log	24.0	24	1.0403	0.0316	1.0403	1.0199
No log	25.0	25	0.9587	0.0382	0.9587	0.9791
No log	26.0	26	0.9068	0.0484	0.9068	0.9523
No log	27.0	27	0.8533	0.1868	0.8533	0.9238
No log	28.0	28	0.7648	0.4033	0.7648	0.8745
No log	29.0	29	0.7343	0.4547	0.7343	0.8569
No log	30.0	30	0.7603	0.3904	0.7603	0.8719
No log	31.0	31	0.8029	0.3827	0.8029	0.8961
No log	32.0	32	0.7019	0.4852	0.7019	0.8378
No log	33.0	33	0.6138	0.4551	0.6138	0.7835
No log	34.0	34	0.5976	0.4523	0.5976	0.7731
No log	35.0	35	0.6071	0.5144	0.6071	0.7792
No log	36.0	36	0.9589	0.4104	0.9589	0.9792
No log	37.0	37	1.1003	0.3599	1.1003	1.0490
No log	38.0	38	0.8754	0.4068	0.8754	0.9356
No log	39.0	39	0.5961	0.5144	0.5961	0.7721
No log	40.0	40	0.5613	0.5002	0.5613	0.7492
No log	41.0	41	0.6087	0.4988	0.6087	0.7802
No log	42.0	42	0.8077	0.4326	0.8077	0.8987
No log	43.0	43	0.9335	0.3958	0.9335	0.9662
No log	44.0	44	0.8524	0.3996	0.8524	0.9233
No log	45.0	45	0.6743	0.4858	0.6743	0.8212
No log	46.0	46	0.6761	0.4746	0.6761	0.8223
No log	47.0	47	0.7430	0.4333	0.7430	0.8620
No log	48.0	48	0.7731	0.4140	0.7731	0.8793
No log	49.0	49	0.9369	0.3848	0.9369	0.9679
No log	50.0	50	0.9340	0.3776	0.9340	0.9664
No log	51.0	51	0.8041	0.3842	0.8041	0.8967
No log	52.0	52	0.7657	0.3875	0.7657	0.8750
No log	53.0	53	0.8315	0.3624	0.8315	0.9119
No log	54.0	54	0.9206	0.3413	0.9206	0.9595
No log	55.0	55	0.9621	0.3265	0.9621	0.9809
No log	56.0	56	0.8604	0.3532	0.8604	0.9276
No log	57.0	57	0.7423	0.4008	0.7423	0.8616
No log	58.0	58	0.7310	0.4449	0.7310	0.8550
No log	59.0	59	0.7518	0.4494	0.7518	0.8671
No log	60.0	60	0.7723	0.4345	0.7723	0.8788
No log	61.0	61	0.8527	0.3750	0.8527	0.9234
No log	62.0	62	0.9940	0.3258	0.9940	0.9970
No log	63.0	63	1.0460	0.3366	1.0460	1.0228
No log	64.0	64	0.9804	0.3444	0.9804	0.9901
No log	65.0	65	0.8786	0.3792	0.8786	0.9373
No log	66.0	66	0.8433	0.4086	0.8433	0.9183
No log	67.0	67	0.8306	0.4130	0.8306	0.9114
No log	68.0	68	0.8338	0.4101	0.8338	0.9131
No log	69.0	69	0.9059	0.3887	0.9059	0.9518

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_fold0

BERT_V8_sp10_lw40_ex10_lo00_k1_k1_fold0

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_fold0