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	9.4489	0.0	9.4470	3.0736
No log	2.0	12	7.7877	0.0	7.7860	2.7903
No log	3.0	18	5.1951	0.0014	5.1938	2.2790
No log	4.0	24	2.5416	0.1115	2.5409	1.5940
No log	5.0	30	1.2091	0.0	1.2086	1.0994
No log	6.0	36	0.8381	0.2303	0.8379	0.9154
No log	7.0	42	1.0501	0.0696	1.0498	1.0246
No log	8.0	48	1.1346	0.0168	1.1342	1.0650
No log	9.0	54	0.8404	0.1734	0.8405	0.9168
No log	10.0	60	0.5898	0.4153	0.5899	0.7680
No log	11.0	66	0.6506	0.4998	0.6509	0.8068
No log	12.0	72	0.6335	0.5415	0.6339	0.7962
No log	13.0	78	0.9521	0.4143	0.9523	0.9759
No log	14.0	84	0.8092	0.4847	0.8093	0.8996
No log	15.0	90	0.7260	0.4526	0.7264	0.8523
No log	16.0	96	0.9138	0.3461	0.9140	0.9560
No log	17.0	102	0.6838	0.4858	0.6841	0.8271
No log	18.0	108	0.8586	0.3697	0.8588	0.9267
No log	19.0	114	1.1163	0.3500	1.1164	1.0566
No log	20.0	120	0.7902	0.4051	0.7903	0.8890
No log	21.0	126	0.7217	0.4243	0.7220	0.8497
No log	22.0	132	0.8253	0.4056	0.8255	0.9086
No log	23.0	138	0.9913	0.3401	0.9915	0.9957
No log	24.0	144	0.9538	0.3880	0.9539	0.9767
No log	25.0	150	0.8199	0.4174	0.8200	0.9056
No log	26.0	156	0.6443	0.4809	0.6445	0.8028
No log	27.0	162	0.6660	0.4595	0.6662	0.8162
No log	28.0	168	0.7575	0.4113	0.7577	0.8705
No log	29.0	174	0.7841	0.4227	0.7842	0.8855
No log	30.0	180	0.8372	0.4163	0.8374	0.9151
No log	31.0	186	0.6919	0.4599	0.6922	0.8320
No log	32.0	192	0.6869	0.4541	0.6872	0.8290
No log	33.0	198	0.6591	0.4497	0.6593	0.8120
No log	34.0	204	0.6832	0.4355	0.6833	0.8266
No log	35.0	210	0.6418	0.4762	0.6421	0.8013
No log	36.0	216	0.6626	0.4843	0.6629	0.8142
No log	37.0	222	0.7362	0.4370	0.7365	0.8582
No log	38.0	228	0.7250	0.4323	0.7253	0.8516
No log	39.0	234	0.6468	0.4750	0.6470	0.8044
No log	40.0	240	0.7584	0.4259	0.7587	0.8710
No log	41.0	246	0.8619	0.4236	0.8622	0.9286
No log	42.0	252	0.9504	0.3877	0.9508	0.9751

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo100_k10_k10_fold3

BERT_V8_sp10_lw20_ex200_lo100_k10_k10_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo100_k10_k10_fold3