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	12.6398	0.0	12.6400	3.5553
No log	2.0	4	10.8031	0.0105	10.8034	3.2868
No log	3.0	6	8.6001	0.0	8.6006	2.9327
No log	4.0	8	6.4781	0.0142	6.4784	2.5453
No log	5.0	10	4.5994	0.0388	4.5998	2.1447
No log	6.0	12	3.4137	0.0105	3.4139	1.8477
No log	7.0	14	2.4962	0.0704	2.4967	1.5801
No log	8.0	16	1.8909	0.1063	1.8914	1.3753
No log	9.0	18	1.3683	0.0551	1.3687	1.1699
No log	10.0	20	1.1326	0.0280	1.1331	1.0645
No log	11.0	22	0.9302	0.0099	0.9306	0.9647
No log	12.0	24	0.7953	0.3113	0.7957	0.8920
No log	13.0	26	0.7624	0.1503	0.7628	0.8734
No log	14.0	28	0.7012	0.1999	0.7014	0.8375
No log	15.0	30	0.7214	0.1999	0.7216	0.8495
No log	16.0	32	0.5882	0.3820	0.5882	0.7670
No log	17.0	34	0.6376	0.4057	0.6375	0.7984
No log	18.0	36	0.7491	0.4724	0.7490	0.8654
No log	19.0	38	0.7118	0.5160	0.7115	0.8435
No log	20.0	40	0.8308	0.4901	0.8304	0.9112
No log	21.0	42	0.9750	0.4562	0.9745	0.9872
No log	22.0	44	0.7401	0.5673	0.7396	0.8600
No log	23.0	46	0.9791	0.5411	0.9784	0.9891
No log	24.0	48	0.9164	0.5645	0.9156	0.9568
No log	25.0	50	0.7269	0.5927	0.7263	0.8522
No log	26.0	52	1.0924	0.5199	1.0914	1.0447
No log	27.0	54	1.0710	0.5329	1.0702	1.0345
No log	28.0	56	0.5946	0.6359	0.5942	0.7708
No log	29.0	58	0.7578	0.5891	0.7571	0.8701
No log	30.0	60	0.7284	0.5969	0.7278	0.8531
No log	31.0	62	0.5957	0.6216	0.5954	0.7716
No log	32.0	64	0.8335	0.5618	0.8328	0.9126
No log	33.0	66	0.8091	0.5613	0.8085	0.8992
No log	34.0	68	0.5629	0.6201	0.5627	0.7501
No log	35.0	70	0.7749	0.5753	0.7744	0.8800
No log	36.0	72	0.7029	0.5938	0.7024	0.8381
No log	37.0	74	0.9253	0.5533	0.9246	0.9616
No log	38.0	76	0.7418	0.5962	0.7413	0.8610
No log	39.0	78	0.5695	0.6312	0.5692	0.7545
No log	40.0	80	0.6583	0.6208	0.6578	0.8110
No log	41.0	82	1.1398	0.5243	1.1389	1.0672
No log	42.0	84	0.9054	0.5832	0.9046	0.9511
No log	43.0	86	0.6183	0.6444	0.6179	0.7861
No log	44.0	88	0.6590	0.6115	0.6585	0.8115
No log	45.0	90	0.9829	0.5508	0.9822	0.9911
No log	46.0	92	0.7469	0.5803	0.7464	0.8639
No log	47.0	94	0.6505	0.5997	0.6500	0.8062
No log	48.0	96	0.7313	0.5916	0.7306	0.8548
No log	49.0	98	0.6526	0.6237	0.6521	0.8075
No log	50.0	100	0.6756	0.5938	0.6750	0.8216
No log	51.0	102	0.8447	0.5652	0.8441	0.9187
No log	52.0	104	0.6595	0.6009	0.6590	0.8118
No log	53.0	106	0.6657	0.6004	0.6653	0.8156
No log	54.0	108	0.8118	0.5732	0.8113	0.9007
No log	55.0	110	0.9154	0.5616	0.9148	0.9565
No log	56.0	112	0.6568	0.6039	0.6564	0.8102
No log	57.0	114	0.6434	0.6069	0.6430	0.8019
No log	58.0	116	0.8227	0.5514	0.8221	0.9067
No log	59.0	118	0.7641	0.5712	0.7636	0.8738
No log	60.0	120	0.5727	0.6165	0.5724	0.7566
No log	61.0	122	0.5751	0.6243	0.5748	0.7582
No log	62.0	124	0.6819	0.6047	0.6814	0.8255
No log	63.0	126	0.9119	0.5643	0.9113	0.9546

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version12AGAINNNASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_fold2

Version12AGAINNNASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version12AGAINNNASAP_FineTuningBERT_AugV12_k5_task1_organization_k5_k5_fold2