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	5	6.2377	0.0084	6.2358	2.4972
No log	2.0	10	3.3481	0.0	3.3462	1.8293
No log	3.0	15	1.7914	0.0583	1.7898	1.3378
No log	4.0	20	1.0343	0.0	1.0329	1.0163
No log	5.0	25	0.8695	0.3458	0.8684	0.9319
No log	6.0	30	1.1236	0.0106	1.1222	1.0593
No log	7.0	35	0.6666	0.4224	0.6655	0.8158
No log	8.0	40	1.0065	0.2508	1.0051	1.0026
No log	9.0	45	0.8341	0.2035	0.8332	0.9128
No log	10.0	50	0.9038	0.2327	0.9026	0.9501
No log	11.0	55	0.7161	0.3070	0.7154	0.8458
No log	12.0	60	0.5384	0.5160	0.5376	0.7332
No log	13.0	65	0.5565	0.5035	0.5559	0.7456
No log	14.0	70	0.5694	0.5358	0.5687	0.7541
No log	15.0	75	0.6284	0.4713	0.6277	0.7923
No log	16.0	80	0.6770	0.4425	0.6764	0.8224
No log	17.0	85	0.6221	0.4618	0.6214	0.7883
No log	18.0	90	0.6772	0.4662	0.6765	0.8225
No log	19.0	95	0.6495	0.4960	0.6489	0.8055
No log	20.0	100	0.8158	0.4205	0.8151	0.9028
No log	21.0	105	0.7238	0.4291	0.7231	0.8503
No log	22.0	110	0.6584	0.4439	0.6577	0.8110
No log	23.0	115	0.6238	0.4692	0.6231	0.7894
No log	24.0	120	0.8509	0.3993	0.8501	0.9220
No log	25.0	125	0.6890	0.4861	0.6883	0.8296
No log	26.0	130	0.6230	0.4902	0.6223	0.7889
No log	27.0	135	0.6732	0.4838	0.6725	0.8201
No log	28.0	140	0.7805	0.4358	0.7797	0.8830
No log	29.0	145	0.6511	0.4876	0.6504	0.8065
No log	30.0	150	0.8968	0.3444	0.8959	0.9465
No log	31.0	155	0.7838	0.3863	0.7830	0.8849
No log	32.0	160	0.6587	0.4575	0.6579	0.8111
No log	33.0	165	0.8308	0.3884	0.8300	0.9111
No log	34.0	170	0.7365	0.4026	0.7358	0.8578
No log	35.0	175	0.7362	0.3750	0.7354	0.8576
No log	36.0	180	0.7828	0.4201	0.7820	0.8843
No log	37.0	185	0.6983	0.4876	0.6976	0.8352
No log	38.0	190	0.7126	0.4247	0.7118	0.8437
No log	39.0	195	0.7219	0.4188	0.7211	0.8492
No log	40.0	200	0.8611	0.3834	0.8603	0.9275
No log	41.0	205	0.6251	0.4708	0.6244	0.7902
No log	42.0	210	1.0414	0.3177	1.0404	1.0200
No log	43.0	215	0.6627	0.4000	0.6620	0.8136
No log	44.0	220	0.8269	0.3301	0.8260	0.9088

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex30_lo00_k7_k7_fold1

BERT_V8_sp10_lw40_ex30_lo00_k7_k7_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex30_lo00_k7_k7_fold1