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	4.1823	0.0079	4.1803	2.0446
No log	2.0	12	1.9949	0.0315	1.9933	1.4118
No log	3.0	18	1.0718	0.0	1.0705	1.0346
No log	4.0	24	0.8810	0.3020	0.8797	0.9379
No log	5.0	30	0.9713	0.2346	0.9699	0.9848
No log	6.0	36	1.2592	0.1510	1.2578	1.1215
No log	7.0	42	1.0182	0.3019	1.0165	1.0082
No log	8.0	48	0.9818	0.2584	0.9802	0.9900
No log	9.0	54	1.0299	0.2486	1.0286	1.0142
No log	10.0	60	0.8995	0.3521	0.8984	0.9478
No log	11.0	66	0.8386	0.3755	0.8378	0.9153
No log	12.0	72	0.8004	0.4115	0.7998	0.8943
No log	13.0	78	0.9456	0.3857	0.9445	0.9719
No log	14.0	84	0.7854	0.3753	0.7845	0.8857
No log	15.0	90	0.9336	0.3993	0.9329	0.9659
No log	16.0	96	1.1054	0.3205	1.1038	1.0506
No log	17.0	102	0.8053	0.4132	0.8042	0.8968
No log	18.0	108	0.8986	0.3393	0.8973	0.9472
No log	19.0	114	1.2014	0.2944	1.1999	1.0954
No log	20.0	120	0.8775	0.4393	0.8767	0.9363
No log	21.0	126	0.7942	0.4191	0.7934	0.8907
No log	22.0	132	0.8462	0.3938	0.8452	0.9193
No log	23.0	138	0.8305	0.3766	0.8296	0.9108
No log	24.0	144	0.8631	0.3576	0.8621	0.9285
No log	25.0	150	0.8553	0.3621	0.8542	0.9242
No log	26.0	156	0.8442	0.3942	0.8433	0.9183
No log	27.0	162	0.9106	0.3683	0.9097	0.9538
No log	28.0	168	0.9192	0.3239	0.9181	0.9582
No log	29.0	174	0.8897	0.3396	0.8888	0.9428
No log	30.0	180	0.8529	0.3752	0.8517	0.9229
No log	31.0	186	0.8861	0.3893	0.8847	0.9406
No log	32.0	192	0.8756	0.3268	0.8744	0.9351
No log	33.0	198	0.8422	0.3745	0.8411	0.9171
No log	34.0	204	0.8737	0.3936	0.8725	0.9341
No log	35.0	210	0.9549	0.3568	0.9535	0.9765
No log	36.0	216	0.9548	0.3148	0.9534	0.9764
No log	37.0	222	0.9018	0.3540	0.9007	0.9491
No log	38.0	228	0.8666	0.3599	0.8655	0.9303
No log	39.0	234	0.8473	0.3692	0.8460	0.9198
No log	40.0	240	0.8511	0.3903	0.8497	0.9218
No log	41.0	246	0.8381	0.4043	0.8368	0.9148
No log	42.0	252	0.9783	0.3281	0.9770	0.9884
No log	43.0	258	0.9328	0.2977	0.9316	0.9652
No log	44.0	264	0.9273	0.3107	0.9260	0.9623
No log	45.0	270	0.9915	0.3255	0.9901	0.9950
No log	46.0	276	0.9780	0.3286	0.9766	0.9882
No log	47.0	282	1.0354	0.3214	1.0340	1.0169
No log	48.0	288	0.7979	0.3678	0.7968	0.8927
No log	49.0	294	0.8227	0.3810	0.8216	0.9064
No log	50.0	300	0.8354	0.3598	0.8342	0.9133

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_k10_k10_fold1

BERT_V8_sp10_lw40_ex50_lo100_k10_k10_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k10_k10_fold1