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	9.9840	0.0023	9.9813	3.1593
No log	2.0	4	7.2620	0.0	7.2595	2.6943
No log	3.0	6	5.4788	0.0328	5.4768	2.3403
No log	4.0	8	4.1887	0.0	4.1868	2.0462
No log	5.0	10	3.6058	0.0	3.6042	1.8985
No log	6.0	12	2.6697	0.0	2.6681	1.6334
No log	7.0	14	2.3144	0.0637	2.3127	1.5208
No log	8.0	16	1.9739	0.0615	1.9722	1.4044
No log	9.0	18	1.5910	0.0	1.5894	1.2607
No log	10.0	20	1.3130	0.0	1.3115	1.1452
No log	11.0	22	1.1154	0.0	1.1140	1.0555
No log	12.0	24	1.0336	0.0	1.0322	1.0160
No log	13.0	26	1.1157	0.0025	1.1141	1.0555
No log	14.0	28	1.1151	0.0527	1.1137	1.0553
No log	15.0	30	1.0214	0.1555	1.0204	1.0101
No log	16.0	32	1.0300	0.2059	1.0290	1.0144
No log	17.0	34	1.2138	0.0314	1.2128	1.1013
No log	18.0	36	1.1710	0.0933	1.1701	1.0817
No log	19.0	38	1.1464	0.1400	1.1456	1.0703
No log	20.0	40	1.5288	0.1357	1.5279	1.2361
No log	21.0	42	1.3120	0.1974	1.3112	1.1451
No log	22.0	44	1.1695	0.1111	1.1688	1.0811
No log	23.0	46	1.3551	0.0173	1.3543	1.1638
No log	24.0	48	1.1229	0.1784	1.1225	1.0595
No log	25.0	50	1.0869	0.2994	1.0866	1.0424
No log	26.0	52	1.0000	0.3419	0.9999	1.0000
No log	27.0	54	1.3595	0.1330	1.3593	1.1659
No log	28.0	56	1.9388	-0.0041	1.9386	1.3923
No log	29.0	58	1.8900	0.0441	1.8900	1.3748
No log	30.0	60	1.2049	0.3319	1.2051	1.0978
No log	31.0	62	1.0605	0.3568	1.0608	1.0300
No log	32.0	64	1.3668	0.2225	1.3670	1.1692
No log	33.0	66	1.3752	0.2340	1.3753	1.1727
No log	34.0	68	1.1660	0.3036	1.1663	1.0799
No log	35.0	70	1.3142	0.2879	1.3144	1.1465
No log	36.0	72	1.2424	0.2841	1.2427	1.1148
No log	37.0	74	1.2581	0.2924	1.2587	1.1219
No log	38.0	76	1.3353	0.2579	1.3358	1.1558
No log	39.0	78	1.5245	0.1475	1.5246	1.2348
No log	40.0	80	1.2516	0.2772	1.2521	1.1190
No log	41.0	82	1.0989	0.3505	1.0996	1.0486
No log	42.0	84	1.2646	0.2933	1.2651	1.1248
No log	43.0	86	1.5268	0.1606	1.5268	1.2356
No log	44.0	88	1.4664	0.1876	1.4664	1.2110
No log	45.0	90	1.2102	0.3246	1.2107	1.1003
No log	46.0	92	1.1555	0.3804	1.1564	1.0754
No log	47.0	94	1.1047	0.3982	1.1055	1.0514
No log	48.0	96	1.3666	0.2941	1.3671	1.1692
No log	49.0	98	1.5630	0.2048	1.5634	1.2504
No log	50.0	100	1.6027	0.1690	1.6031	1.2661
No log	51.0	102	1.6276	0.1633	1.6279	1.2759
No log	52.0	104	1.4399	0.2548	1.4402	1.2001
No log	53.0	106	1.2845	0.2965	1.2849	1.1336
No log	54.0	108	1.2827	0.3090	1.2832	1.1328
No log	55.0	110	1.4981	0.2331	1.4987	1.2242
No log	56.0	112	1.7723	0.1250	1.7727	1.3314
No log	57.0	114	1.6242	0.1788	1.6246	1.2746
No log	58.0	116	1.4135	0.2616	1.4140	1.1891
No log	59.0	118	1.2441	0.3035	1.2446	1.1156
No log	60.0	120	1.2636	0.2793	1.2640	1.1243
No log	61.0	122	1.2789	0.2793	1.2793	1.1310
No log	62.0	124	1.3659	0.2782	1.3664	1.1689

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_sp020_lw070_fold1

BERT_AugV8_k1_task1_organization_sp020_lw070_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp020_lw070_fold1