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	12	4.3177	0.0	4.3165	2.0776
No log	2.0	24	1.7468	0.0	1.7460	1.3214
No log	3.0	36	1.2336	0.0202	1.2329	1.1104
No log	4.0	48	2.6526	-0.0158	2.6519	1.6285
No log	5.0	60	0.8957	0.3020	0.8957	0.9464
No log	6.0	72	0.9686	0.1471	0.9689	0.9843
No log	7.0	84	1.0512	0.1150	1.0515	1.0254
No log	8.0	96	1.6756	0.1076	1.6759	1.2946
No log	9.0	108	1.4547	0.1685	1.4553	1.2063
No log	10.0	120	2.9544	-0.0103	2.9544	1.7188
No log	11.0	132	0.7863	0.3824	0.7862	0.8867
No log	12.0	144	1.1001	0.2874	1.1004	1.0490
No log	13.0	156	1.3580	0.1928	1.3579	1.1653
No log	14.0	168	0.9877	0.2554	0.9877	0.9938
No log	15.0	180	0.7682	0.3629	0.7681	0.8764
No log	16.0	192	1.4556	0.1886	1.4559	1.2066
No log	17.0	204	0.9141	0.2972	0.9141	0.9561
No log	18.0	216	0.7577	0.3471	0.7575	0.8704
No log	19.0	228	0.8113	0.3419	0.8113	0.9007
No log	20.0	240	1.4920	0.1772	1.4923	1.2216
No log	21.0	252	0.8067	0.3943	0.8068	0.8982
No log	22.0	264	1.1380	0.2834	1.1380	1.0668
No log	23.0	276	1.2843	0.1867	1.2843	1.1333
No log	24.0	288	0.8794	0.2975	0.8793	0.9377
No log	25.0	300	1.0836	0.2600	1.0836	1.0410
No log	26.0	312	0.8268	0.3681	0.8268	0.9093
No log	27.0	324	0.8862	0.2972	0.8861	0.9413
No log	28.0	336	1.2452	0.2443	1.2453	1.1159
No log	29.0	348	0.9887	0.2635	0.9888	0.9944
No log	30.0	360	0.9545	0.2661	0.9545	0.9770
No log	31.0	372	0.9238	0.3451	0.9238	0.9612
No log	32.0	384	1.0159	0.2912	1.0160	1.0079
No log	33.0	396	0.8659	0.3269	0.8659	0.9306
No log	34.0	408	1.0563	0.2602	1.0564	1.0278
No log	35.0	420	1.1643	0.2621	1.1645	1.0791
No log	36.0	432	1.0443	0.3018	1.0442	1.0219
No log	37.0	444	1.6820	0.1463	1.6819	1.2969
No log	38.0	456	1.1880	0.2111	1.1879	1.0899
No log	39.0	468	1.1419	0.2713	1.1420	1.0687
No log	40.0	480	0.7968	0.3603	0.7968	0.8926
No log	41.0	492	0.7478	0.4096	0.7479	0.8648
0.4449	42.0	504	0.8224	0.3978	0.8226	0.9070
0.4449	43.0	516	1.0730	0.2590	1.0731	1.0359
0.4449	44.0	528	1.2496	0.2192	1.2497	1.1179
0.4449	45.0	540	1.1699	0.2479	1.1700	1.0816
0.4449	46.0	552	0.8734	0.3145	0.8734	0.9346
0.4449	47.0	564	1.0720	0.2570	1.0721	1.0354
0.4449	48.0	576	0.8941	0.3281	0.8941	0.9456
0.4449	49.0	588	1.2107	0.2168	1.2107	1.1003
0.4449	50.0	600	1.1439	0.2402	1.1440	1.0696
0.4449	51.0	612	1.0263	0.2701	1.0264	1.0131
0.4449	52.0	624	0.9158	0.3248	0.9159	0.9570
0.4449	53.0	636	0.8811	0.3122	0.8811	0.9387
0.4449	54.0	648	0.9434	0.3104	0.9434	0.9713
0.4449	55.0	660	1.0317	0.2935	1.0318	1.0158
0.4449	56.0	672	0.9503	0.2996	0.9503	0.9748
0.4449	57.0	684	0.9727	0.2883	0.9727	0.9862
0.4449	58.0	696	0.8393	0.3392	0.8394	0.9162
0.4449	59.0	708	0.9427	0.2957	0.9428	0.9710
0.4449	60.0	720	0.8631	0.3505	0.8632	0.9291
0.4449	61.0	732	0.8070	0.3681	0.8071	0.8984

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

genki10/ASAP_FineTuningBERT_AugV6_k15_task1_organization_k15_k15_fold3

ASAP_FineTuningBERT_AugV6_k15_task1_organization_k15_k15_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
ASAP_FineTuningBERT_AugV6_k15_task1_organization_k15_k15_fold3