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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	11.0609	-0.0246	11.0581	3.3254
No log	2.0	4	9.1970	0.0	9.1945	3.0322
No log	3.0	6	7.6891	0.0	7.6869	2.7725
No log	4.0	8	6.4658	0.0	6.4636	2.5424
No log	5.0	10	5.3893	0.0317	5.3872	2.3210
No log	6.0	12	4.7230	0.0040	4.7209	2.1728
No log	7.0	14	3.9717	0.0	3.9697	1.9924
No log	8.0	16	3.3188	0.0	3.3169	1.8212
No log	9.0	18	2.7188	0.0	2.7169	1.6483
No log	10.0	20	2.2122	0.0819	2.2104	1.4868
No log	11.0	22	1.8039	0.0106	1.8023	1.3425
No log	12.0	24	1.5139	0.0	1.5123	1.2298
No log	13.0	26	1.3148	0.0	1.3133	1.1460
No log	14.0	28	1.1138	0.0	1.1124	1.0547
No log	15.0	30	0.9666	0.0	0.9653	0.9825
No log	16.0	32	0.8961	0.3274	0.8949	0.9460
No log	17.0	34	0.8559	0.3327	0.8546	0.9245
No log	18.0	36	0.8228	0.3322	0.8217	0.9065
No log	19.0	38	0.9009	0.1115	0.8996	0.9485
No log	20.0	40	0.6812	0.4117	0.6802	0.8247
No log	21.0	42	0.6031	0.4769	0.6021	0.7760
No log	22.0	44	0.8063	0.4072	0.8051	0.8973
No log	23.0	46	1.2353	0.2657	1.2339	1.1108
No log	24.0	48	0.9313	0.4073	0.9300	0.9644
No log	25.0	50	0.8486	0.2223	0.8476	0.9206
No log	26.0	52	1.0344	0.0297	1.0332	1.0165
No log	27.0	54	0.7828	0.3704	0.7816	0.8841
No log	28.0	56	0.5736	0.4718	0.5726	0.7567
No log	29.0	58	0.6224	0.4862	0.6213	0.7883
No log	30.0	60	0.5666	0.5271	0.5656	0.7521
No log	31.0	62	0.5570	0.5232	0.5561	0.7457
No log	32.0	64	0.6953	0.5187	0.6941	0.8331
No log	33.0	66	0.6783	0.4835	0.6773	0.8230
No log	34.0	68	0.8710	0.4053	0.8697	0.9326
No log	35.0	70	1.2129	0.2689	1.2112	1.1006
No log	36.0	72	1.0372	0.3051	1.0362	1.0179
No log	37.0	74	1.1682	0.2246	1.1669	1.0802
No log	38.0	76	1.0831	0.2477	1.0818	1.0401
No log	39.0	78	0.8891	0.3234	0.8880	0.9424
No log	40.0	80	0.8563	0.3209	0.8553	0.9249
No log	41.0	82	0.9955	0.3251	0.9943	0.9971
No log	42.0	84	1.0580	0.3270	1.0569	1.0281
No log	43.0	86	0.9852	0.3586	0.9842	0.9921
No log	44.0	88	1.1155	0.3359	1.1137	1.0553
No log	45.0	90	1.4638	0.2736	1.4614	1.2089
No log	46.0	92	1.4128	0.2863	1.4104	1.1876
No log	47.0	94	0.9596	0.4367	0.9580	0.9788
No log	48.0	96	0.8641	0.4562	0.8629	0.9289
No log	49.0	98	1.1770	0.3625	1.1750	1.0840
No log	50.0	100	1.2169	0.3426	1.2148	1.1022
No log	51.0	102	0.9482	0.4327	0.9469	0.9731
No log	52.0	104	0.9352	0.4433	0.9341	0.9665
No log	53.0	106	1.0169	0.4100	1.0155	1.0077
No log	54.0	108	1.1324	0.3453	1.1308	1.0634
No log	55.0	110	0.9695	0.4100	0.9684	0.9841
No log	56.0	112	0.9382	0.4221	0.9370	0.9680
No log	57.0	114	1.1290	0.3418	1.1272	1.0617
No log	58.0	116	1.1116	0.3540	1.1099	1.0535
No log	59.0	118	0.9283	0.4321	0.9272	0.9629
No log	60.0	120	0.8874	0.4616	0.8866	0.9416

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold1

BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold1