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	3	9.8380	0.0084	9.8380	3.1366
No log	2.0	6	7.9717	0.0018	7.9717	2.8234
No log	3.0	9	6.0384	0.0293	6.0384	2.4573
No log	4.0	12	4.2514	0.0139	4.2514	2.0619
No log	5.0	15	3.1394	0.0115	3.1394	1.7718
No log	6.0	18	2.3184	0.1330	2.3184	1.5226
No log	7.0	21	1.7284	0.0583	1.7284	1.3147
No log	8.0	24	1.3258	0.0316	1.3258	1.1514
No log	9.0	27	1.2802	0.0923	1.2802	1.1315
No log	10.0	30	1.3940	0.1565	1.3940	1.1807
No log	11.0	33	1.0211	0.1290	1.0211	1.0105
No log	12.0	36	2.8006	0.1129	2.8006	1.6735
No log	13.0	39	1.1338	0.1690	1.1338	1.0648
No log	14.0	42	1.2145	0.1626	1.2145	1.1020
No log	15.0	45	1.6093	0.1951	1.6093	1.2686
No log	16.0	48	0.8148	0.3998	0.8148	0.9027
No log	17.0	51	1.2563	0.2490	1.2563	1.1208
No log	18.0	54	0.7563	0.4499	0.7563	0.8697
No log	19.0	57	1.0672	0.3779	1.0672	1.0330
No log	20.0	60	0.8199	0.4106	0.8199	0.9055
No log	21.0	63	0.9892	0.3804	0.9892	0.9946
No log	22.0	66	0.8848	0.3793	0.8848	0.9406
No log	23.0	69	0.8698	0.4121	0.8698	0.9326
No log	24.0	72	1.7075	0.2796	1.7075	1.3067
No log	25.0	75	0.9434	0.4219	0.9434	0.9713
No log	26.0	78	1.2632	0.3325	1.2632	1.1239
No log	27.0	81	0.8100	0.4473	0.8100	0.9000
No log	28.0	84	1.3517	0.3287	1.3517	1.1626
No log	29.0	87	0.8120	0.4680	0.8120	0.9011
No log	30.0	90	0.9315	0.3948	0.9315	0.9651
No log	31.0	93	0.8209	0.4366	0.8209	0.9060
No log	32.0	96	0.8505	0.4065	0.8505	0.9222
No log	33.0	99	0.8652	0.4203	0.8652	0.9302
No log	34.0	102	1.0551	0.4104	1.0551	1.0272
No log	35.0	105	0.8190	0.4826	0.8190	0.9050
No log	36.0	108	0.9263	0.4622	0.9263	0.9624
No log	37.0	111	0.7856	0.4629	0.7856	0.8863
No log	38.0	114	0.9941	0.4448	0.9941	0.9970
No log	39.0	117	0.8481	0.4442	0.8481	0.9209
No log	40.0	120	0.8477	0.4499	0.8477	0.9207
No log	41.0	123	0.7953	0.4704	0.7953	0.8918
No log	42.0	126	0.9428	0.4424	0.9428	0.9710
No log	43.0	129	0.8660	0.4832	0.8660	0.9306
No log	44.0	132	0.8082	0.4777	0.8082	0.8990
No log	45.0	135	0.7782	0.4665	0.7782	0.8821
No log	46.0	138	0.7696	0.4549	0.7696	0.8773
No log	47.0	141	0.7972	0.4488	0.7972	0.8929
No log	48.0	144	0.7746	0.4686	0.7746	0.8801
No log	49.0	147	0.7903	0.4737	0.7903	0.8890
No log	50.0	150	0.7881	0.4642	0.7881	0.8878
No log	51.0	153	0.8368	0.4458	0.8368	0.9148
No log	52.0	156	0.8383	0.4718	0.8383	0.9156
No log	53.0	159	0.8082	0.4535	0.8082	0.8990
No log	54.0	162	0.7745	0.4892	0.7745	0.8801
No log	55.0	165	0.9151	0.4627	0.9151	0.9566
No log	56.0	168	0.8922	0.4897	0.8922	0.9446
No log	57.0	171	0.7931	0.5036	0.7931	0.8906
No log	58.0	174	0.8740	0.4795	0.8740	0.9349
No log	59.0	177	0.7580	0.4588	0.7580	0.8706
No log	60.0	180	0.7648	0.4736	0.7648	0.8745
No log	61.0	183	0.7943	0.4845	0.7943	0.8912
No log	62.0	186	0.7915	0.4926	0.7915	0.8897
No log	63.0	189	0.7864	0.4825	0.7864	0.8868
No log	64.0	192	0.7384	0.4619	0.7384	0.8593
No log	65.0	195	0.7477	0.4848	0.7477	0.8647
No log	66.0	198	0.7570	0.4746	0.7570	0.8701
No log	67.0	201	0.7787	0.4837	0.7787	0.8825
No log	68.0	204	0.7601	0.4773	0.7601	0.8719
No log	69.0	207	0.7486	0.4874	0.7486	0.8652
No log	70.0	210	0.7797	0.4845	0.7797	0.8830
No log	71.0	213	0.8315	0.4744	0.8315	0.9119
No log	72.0	216	0.7802	0.4648	0.7802	0.8833
No log	73.0	219	0.7536	0.4715	0.7536	0.8681
No log	74.0	222	0.7400	0.4849	0.7400	0.8602
No log	75.0	225	0.7122	0.4850	0.7122	0.8439
No log	76.0	228	0.7191	0.4971	0.7191	0.8480
No log	77.0	231	0.7165	0.4854	0.7165	0.8464

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

genki10/ASAP_FineTuningBERT_AugV10_k3_task1_organization_k3_k3_fold0

ASAP_FineTuningBERT_AugV10_k3_task1_organization_k3_k3_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
ASAP_FineTuningBERT_AugV10_k3_task1_organization_k3_k3_fold0