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	3	9.0664	0.0018	9.0667	3.0111
No log	2.0	6	6.0245	0.0006	6.0249	2.4546
No log	3.0	9	3.8031	0.0078	3.8036	1.9503
No log	4.0	12	2.7556	0.0069	2.7561	1.6602
No log	5.0	15	1.6382	0.0411	1.6387	1.2801
No log	6.0	18	1.2207	0.0213	1.2212	1.1051
No log	7.0	21	1.0982	0.0213	1.0987	1.0482
No log	8.0	24	0.9915	0.0147	0.9920	0.9960
No log	9.0	27	1.1407	0.0809	1.1411	1.0682
No log	10.0	30	0.9104	0.2473	0.9106	0.9543
No log	11.0	33	0.7854	0.2905	0.7857	0.8864
No log	12.0	36	1.0035	0.1454	1.0037	1.0018
No log	13.0	39	0.6517	0.4905	0.6518	0.8073
No log	14.0	42	0.5704	0.4535	0.5704	0.7553
No log	15.0	45	0.5927	0.5385	0.5927	0.7698
No log	16.0	48	0.5571	0.5454	0.5570	0.7463
No log	17.0	51	0.6706	0.3599	0.6707	0.8190
No log	18.0	54	0.6759	0.3790	0.6759	0.8222
No log	19.0	57	0.5359	0.5320	0.5358	0.7320
No log	20.0	60	0.5965	0.5217	0.5963	0.7722
No log	21.0	63	0.7790	0.4066	0.7792	0.8827
No log	22.0	66	0.7385	0.4827	0.7387	0.8595
No log	23.0	69	0.6998	0.4555	0.6996	0.8364
No log	24.0	72	0.6006	0.5146	0.6004	0.7748
No log	25.0	75	0.8414	0.3329	0.8416	0.9174
No log	26.0	78	1.2982	0.2904	1.2987	1.1396
No log	27.0	81	1.0276	0.2831	1.0281	1.0140
No log	28.0	84	0.6896	0.4805	0.6897	0.8305
No log	29.0	87	0.6054	0.5543	0.6053	0.7780
No log	30.0	90	0.7941	0.4774	0.7938	0.8909
No log	31.0	93	0.6202	0.5239	0.6202	0.7875
No log	32.0	96	0.8092	0.4280	0.8094	0.8997
No log	33.0	99	0.8575	0.3386	0.8579	0.9262
No log	34.0	102	0.8436	0.3635	0.8439	0.9186
No log	35.0	105	0.7624	0.4483	0.7628	0.8734
No log	36.0	108	0.7556	0.4769	0.7557	0.8693
No log	37.0	111	0.7209	0.4810	0.7208	0.8490
No log	38.0	114	0.6425	0.4895	0.6424	0.8015
No log	39.0	117	0.6247	0.5171	0.6246	0.7903
No log	40.0	120	0.6802	0.5361	0.6800	0.8246
No log	41.0	123	0.6115	0.5698	0.6113	0.7819
No log	42.0	126	0.7979	0.4732	0.7976	0.8931
No log	43.0	129	0.5984	0.5301	0.5984	0.7736
No log	44.0	132	0.7951	0.4098	0.7949	0.8916
No log	45.0	135	0.5414	0.6049	0.5413	0.7357
No log	46.0	138	0.5479	0.6088	0.5477	0.7400
No log	47.0	141	0.8246	0.4330	0.8242	0.9078
No log	48.0	144	0.5259	0.6146	0.5256	0.7250
No log	49.0	147	0.6621	0.5383	0.6618	0.8135
No log	50.0	150	0.6159	0.5402	0.6159	0.7848
No log	51.0	153	0.6779	0.4766	0.6780	0.8234
No log	52.0	156	0.6444	0.4924	0.6445	0.8028
No log	53.0	159	0.6621	0.4866	0.6623	0.8138
No log	54.0	162	0.6543	0.4788	0.6545	0.8090
No log	55.0	165	0.6585	0.4878	0.6587	0.8116
No log	56.0	168	0.6583	0.5108	0.6583	0.8114
No log	57.0	171	0.5938	0.5464	0.5938	0.7706
No log	58.0	174	0.7022	0.4755	0.7021	0.8379
No log	59.0	177	0.5687	0.5562	0.5687	0.7541
No log	60.0	180	0.7680	0.4247	0.7680	0.8763
No log	61.0	183	0.6713	0.4968	0.6713	0.8194
No log	62.0	186	0.6788	0.4954	0.6788	0.8239
No log	63.0	189	0.6025	0.5553	0.6025	0.7762

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_AugV8_k3_task1_organization_sp040_lw030_fold2

BERT_AugV8_k3_task1_organization_sp040_lw030_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k3_task1_organization_sp040_lw030_fold2