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	12.5053	0.0	12.5025	3.5359
No log	2.0	4	11.7809	0.0	11.7782	3.4319
No log	3.0	6	11.2710	-0.0184	11.2684	3.3568
No log	4.0	8	10.5816	0.0	10.5790	3.2525
No log	5.0	10	9.5594	0.0	9.5570	3.0914
No log	6.0	12	8.1278	0.0	8.1254	2.8505
No log	7.0	14	6.7656	0.0	6.7633	2.6006
No log	8.0	16	5.0592	0.0222	5.0571	2.2488
No log	9.0	18	3.3609	0.0	3.3590	1.8327
No log	10.0	20	2.4100	0.0239	2.4083	1.5519
No log	11.0	22	1.9698	0.0841	1.9683	1.4029
No log	12.0	24	1.4700	0.0106	1.4686	1.2118
No log	13.0	26	1.2547	0.0106	1.2533	1.1195
No log	14.0	28	1.2716	0.0106	1.2703	1.1271
No log	15.0	30	1.0766	0.0	1.0753	1.0370
No log	16.0	32	1.0977	0.0211	1.0962	1.0470
No log	17.0	34	1.0483	0.0211	1.0469	1.0232
No log	18.0	36	0.9269	0.0617	0.9257	0.9621
No log	19.0	38	0.9495	0.0446	0.9484	0.9738
No log	20.0	40	0.9214	0.1038	0.9203	0.9593
No log	21.0	42	0.9152	0.1896	0.9139	0.9560
No log	22.0	44	0.9000	0.2720	0.8986	0.9479
No log	23.0	46	0.8587	0.3589	0.8572	0.9258
No log	24.0	48	0.9789	0.3170	0.9773	0.9886
No log	25.0	50	1.0963	0.2893	1.0946	1.0462
No log	26.0	52	1.1276	0.2787	1.1259	1.0611
No log	27.0	54	0.7588	0.4064	0.7578	0.8705
No log	28.0	56	0.7803	0.3683	0.7792	0.8827
No log	29.0	58	1.3062	0.2419	1.3040	1.1419
No log	30.0	60	1.0201	0.3311	1.0184	1.0091
No log	31.0	62	0.8647	0.4437	0.8635	0.9292
No log	32.0	64	0.8704	0.4104	0.8691	0.9323
No log	33.0	66	1.0624	0.3381	1.0605	1.0298
No log	34.0	68	1.0259	0.3449	1.0239	1.0119
No log	35.0	70	0.7867	0.4740	0.7855	0.8863
No log	36.0	72	0.8020	0.4664	0.8006	0.8948
No log	37.0	74	0.9997	0.3743	0.9975	0.9988
No log	38.0	76	0.9190	0.4498	0.9170	0.9576
No log	39.0	78	0.8111	0.5388	0.8099	0.9000
No log	40.0	80	0.6969	0.5385	0.6955	0.8340
No log	41.0	82	0.6353	0.5445	0.6341	0.7963
No log	42.0	84	0.6771	0.5156	0.6757	0.8220
No log	43.0	86	0.7291	0.4765	0.7275	0.8529
No log	44.0	88	0.7879	0.4708	0.7864	0.8868
No log	45.0	90	0.8778	0.3715	0.8758	0.9358
No log	46.0	92	1.1693	0.3303	1.1668	1.0802
No log	47.0	94	0.9881	0.3773	0.9860	0.9930
No log	48.0	96	0.9756	0.3959	0.9736	0.9867
No log	49.0	98	0.8945	0.3968	0.8927	0.9448
No log	50.0	100	0.7969	0.4575	0.7954	0.8919
No log	51.0	102	0.8634	0.4439	0.8617	0.9283
No log	52.0	104	0.8126	0.4957	0.8111	0.9006
No log	53.0	106	0.7716	0.4769	0.7700	0.8775
No log	54.0	108	0.7547	0.4670	0.7534	0.8680
No log	55.0	110	0.7564	0.4589	0.7548	0.8688
No log	56.0	112	0.8628	0.4267	0.8607	0.9277

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_sp040_lw040_fold1

BERT_AugV8_k1_task1_organization_sp040_lw040_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp040_lw040_fold1