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	6	7.3395	0.0	7.3395	2.7092
No log	2.0	12	4.0407	0.0115	4.0407	2.0102
No log	3.0	18	1.8245	0.0474	1.8245	1.3507
No log	4.0	24	1.0443	0.0324	1.0443	1.0219
No log	5.0	30	0.8864	0.1627	0.8864	0.9415
No log	6.0	36	1.4258	0.0687	1.4258	1.1940
No log	7.0	42	0.7230	0.4177	0.7230	0.8503
No log	8.0	48	0.7274	0.2679	0.7274	0.8529
No log	9.0	54	0.7349	0.2827	0.7349	0.8572
No log	10.0	60	0.6784	0.3837	0.6784	0.8236
No log	11.0	66	0.6585	0.4228	0.6585	0.8115
No log	12.0	72	0.6484	0.3744	0.6484	0.8052
No log	13.0	78	0.8274	0.3565	0.8274	0.9096
No log	14.0	84	0.7280	0.3556	0.7280	0.8532
No log	15.0	90	0.6954	0.3725	0.6954	0.8339
No log	16.0	96	0.7473	0.4005	0.7473	0.8645
No log	17.0	102	0.6286	0.4050	0.6286	0.7929
No log	18.0	108	0.7118	0.3490	0.7118	0.8437
No log	19.0	114	0.9043	0.2975	0.9043	0.9510
No log	20.0	120	0.8476	0.3411	0.8476	0.9207
No log	21.0	126	1.0441	0.2277	1.0441	1.0218
No log	22.0	132	1.0646	0.2256	1.0646	1.0318
No log	23.0	138	0.9045	0.2742	0.9045	0.9510
No log	24.0	144	0.9708	0.2720	0.9708	0.9853
No log	25.0	150	0.7800	0.3087	0.7800	0.8832
No log	26.0	156	0.8729	0.2836	0.8729	0.9343
No log	27.0	162	1.0184	0.2339	1.0184	1.0092
No log	28.0	168	0.6940	0.3754	0.6940	0.8331
No log	29.0	174	0.7443	0.3675	0.7443	0.8627
No log	30.0	180	1.0411	0.2276	1.0411	1.0203
No log	31.0	186	0.9368	0.2640	0.9368	0.9679
No log	32.0	192	0.7206	0.3326	0.7206	0.8489
No log	33.0	198	0.7463	0.3269	0.7463	0.8639
No log	34.0	204	0.9339	0.2560	0.9339	0.9664
No log	35.0	210	0.9010	0.2327	0.9010	0.9492
No log	36.0	216	0.8464	0.3248	0.8464	0.9200
No log	37.0	222	0.9427	0.2666	0.9427	0.9709
No log	38.0	228	0.8935	0.2458	0.8935	0.9453
No log	39.0	234	0.7222	0.2960	0.7222	0.8498
No log	40.0	240	0.8034	0.2373	0.8034	0.8963
No log	41.0	246	0.8908	0.2777	0.8908	0.9438

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_k10_k10_fold0

BERT_V8_sp10_lw40_ex10_lo00_k10_k10_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_k10_k10_fold0