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	3	7.6071	0.0018	7.6043	2.7576
No log	2.0	6	6.0717	-0.0016	6.0695	2.4636
No log	3.0	9	4.8432	0.0050	4.8411	2.2002
No log	4.0	12	3.5985	0.0	3.5966	1.8965
No log	5.0	15	2.6452	0.0	2.6433	1.6258
No log	6.0	18	1.9115	0.0260	1.9099	1.3820
No log	7.0	21	1.4602	0.0	1.4587	1.2078
No log	8.0	24	1.0162	0.0	1.0148	1.0074
No log	9.0	27	0.8942	0.1358	0.8931	0.9450
No log	10.0	30	0.8911	0.1703	0.8897	0.9432
No log	11.0	33	0.8216	0.1618	0.8204	0.9058
No log	12.0	36	0.7136	0.2634	0.7127	0.8442
No log	13.0	39	0.6939	0.4036	0.6929	0.8324
No log	14.0	42	0.6724	0.4364	0.6714	0.8194
No log	15.0	45	0.6983	0.3871	0.6974	0.8351
No log	16.0	48	0.6282	0.4805	0.6273	0.7920
No log	17.0	51	0.6282	0.5007	0.6273	0.7921
No log	18.0	54	0.9071	0.4108	0.9064	0.9520
No log	19.0	57	0.6243	0.5477	0.6236	0.7897
No log	20.0	60	0.7769	0.4823	0.7761	0.8810
No log	21.0	63	0.7309	0.4624	0.7301	0.8544
No log	22.0	66	0.5212	0.5254	0.5204	0.7214
No log	23.0	69	0.4626	0.6579	0.4620	0.6797
No log	24.0	72	0.4528	0.6410	0.4521	0.6724
No log	25.0	75	0.4692	0.6095	0.4685	0.6845
No log	26.0	78	0.5651	0.5798	0.5644	0.7513
No log	27.0	81	0.5455	0.5373	0.5447	0.7381
No log	28.0	84	0.5404	0.5236	0.5396	0.7346
No log	29.0	87	0.5858	0.5879	0.5850	0.7649
No log	30.0	90	0.7044	0.5233	0.7037	0.8389
No log	31.0	93	0.5798	0.5164	0.5790	0.7609
No log	32.0	96	0.6961	0.5098	0.6954	0.8339
No log	33.0	99	0.5494	0.5537	0.5485	0.7406
No log	34.0	102	0.5768	0.5560	0.5761	0.7590
No log	35.0	105	0.5841	0.5587	0.5833	0.7637
No log	36.0	108	0.6111	0.5295	0.6104	0.7813
No log	37.0	111	0.5723	0.5342	0.5714	0.7559
No log	38.0	114	0.6323	0.4508	0.6315	0.7947
No log	39.0	117	0.5794	0.4585	0.5785	0.7606
No log	40.0	120	0.6718	0.5183	0.6709	0.8191
No log	41.0	123	0.6329	0.4763	0.6321	0.7951
No log	42.0	126	0.6033	0.5115	0.6024	0.7761
No log	43.0	129	0.5958	0.4551	0.5948	0.7713
No log	44.0	132	0.6317	0.4385	0.6308	0.7943
No log	45.0	135	0.5699	0.5389	0.5690	0.7543
No log	46.0	138	0.5266	0.5514	0.5259	0.7252
No log	47.0	141	0.5124	0.6018	0.5116	0.7153
No log	48.0	144	0.5179	0.5872	0.5171	0.7191
No log	49.0	147	0.5356	0.5387	0.5348	0.7313
No log	50.0	150	0.5571	0.5689	0.5563	0.7459
No log	51.0	153	0.5651	0.5348	0.5643	0.7512
No log	52.0	156	0.5722	0.4633	0.5713	0.7559
No log	53.0	159	0.5567	0.5295	0.5559	0.7456

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold1

BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold1