learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	9.5873	0.0036	9.5855	3.0961
No log	2.0	4	8.7703	0.0	8.7685	2.9612
No log	3.0	6	7.7496	0.0	7.7480	2.7835
No log	4.0	8	6.5834	0.0	6.5819	2.5655
No log	5.0	10	5.5314	0.0161	5.5300	2.3516
No log	6.0	12	4.6377	0.0	4.6364	2.1532
No log	7.0	14	3.8749	0.0	3.8738	1.9682
No log	8.0	16	3.2576	0.0	3.2566	1.8046
No log	9.0	18	2.6874	0.0	2.6865	1.6390
No log	10.0	20	2.2575	0.1234	2.2566	1.5022
No log	11.0	22	2.0716	0.0858	2.0708	1.4390
No log	12.0	24	1.8435	0.0585	1.8427	1.3575
No log	13.0	26	1.4756	0.0365	1.4749	1.2144
No log	14.0	28	1.2724	0.0365	1.2716	1.1277
No log	15.0	30	1.1149	0.0463	1.1143	1.0556
No log	16.0	32	1.4297	0.1412	1.4292	1.1955
No log	17.0	34	1.1924	0.1352	1.1921	1.0918
No log	18.0	36	0.8109	0.3688	0.8107	0.9004
No log	19.0	38	0.8405	0.2774	0.8403	0.9167
No log	20.0	40	1.2204	0.1901	1.2204	1.1047
No log	21.0	42	1.2342	0.2165	1.2343	1.1110
No log	22.0	44	1.1419	0.2851	1.1422	1.0687
No log	23.0	46	0.6776	0.5317	0.6778	0.8233
No log	24.0	48	0.8074	0.4581	0.8077	0.8987
No log	25.0	50	1.1787	0.2794	1.1795	1.0861
No log	26.0	52	0.7330	0.4758	0.7335	0.8564
No log	27.0	54	0.7184	0.4020	0.7186	0.8477
No log	28.0	56	0.6768	0.4505	0.6773	0.8230
No log	29.0	58	1.1201	0.3585	1.1212	1.0589
No log	30.0	60	0.6290	0.5133	0.6295	0.7934
No log	31.0	62	0.5733	0.4908	0.5737	0.7574
No log	32.0	64	0.6326	0.5489	0.6331	0.7957
No log	33.0	66	0.7633	0.4765	0.7641	0.8741
No log	34.0	68	0.6073	0.5033	0.6078	0.7796
No log	35.0	70	0.6621	0.5516	0.6629	0.8142
No log	36.0	72	1.5321	0.3112	1.5334	1.2383
No log	37.0	74	1.1211	0.3927	1.1221	1.0593
No log	38.0	76	0.6362	0.5653	0.6365	0.7978
No log	39.0	78	0.6157	0.5704	0.6160	0.7849
No log	40.0	80	1.3030	0.3543	1.3040	1.1419
No log	41.0	82	1.2541	0.3555	1.2550	1.1203
No log	42.0	84	0.6398	0.5257	0.6404	0.8003
No log	43.0	86	0.6523	0.5673	0.6530	0.8081
No log	44.0	88	0.8154	0.5085	0.8165	0.9036
No log	45.0	90	0.7525	0.5184	0.7534	0.8680
No log	46.0	92	0.7623	0.5012	0.7631	0.8736
No log	47.0	94	0.7398	0.5193	0.7405	0.8605
No log	48.0	96	0.9637	0.4095	0.9645	0.9821
No log	49.0	98	0.7594	0.4787	0.7601	0.8718
No log	50.0	100	0.6558	0.5573	0.6562	0.8100
No log	51.0	102	0.7017	0.5262	0.7023	0.8380
No log	52.0	104	1.1402	0.3375	1.1412	1.0682
No log	53.0	106	0.8381	0.4411	0.8390	0.9160
No log	54.0	108	0.7201	0.5288	0.7206	0.8489

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_AugV8_k1_task1_organization_sp040_lw040_fold3

BERT_AugV8_k1_task1_organization_sp040_lw040_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp040_lw040_fold3