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	11.5995	-0.0174	11.5974	3.4055
No log	2.0	4	10.9950	0.0018	10.9929	3.3155
No log	3.0	6	10.1561	0.0	10.1542	3.1866
No log	4.0	8	9.1834	0.0	9.1816	3.0301
No log	5.0	10	7.9626	0.0	7.9610	2.8215
No log	6.0	12	6.8413	0.0	6.8399	2.6153
No log	7.0	14	6.0130	0.0064	6.0113	2.4518
No log	8.0	16	5.3358	0.0192	5.3346	2.3097
No log	9.0	18	4.6356	0.0	4.6346	2.1528
No log	10.0	20	3.0491	0.0038	3.0482	1.7459
No log	11.0	22	3.2145	-0.0007	3.2126	1.7924
No log	12.0	24	2.3339	0.0347	2.3328	1.5273
No log	13.0	26	2.1703	0.1327	2.1699	1.4730
No log	14.0	28	2.3872	0.1092	2.3867	1.5449
No log	15.0	30	1.7471	0.0366	1.7467	1.3216
No log	16.0	32	1.0925	0.0	1.0922	1.0451
No log	17.0	34	1.2035	-0.0034	1.2026	1.0966
No log	18.0	36	1.2126	-0.0159	1.2116	1.1007
No log	19.0	38	0.8721	0.2719	0.8718	0.9337
No log	20.0	40	0.9383	0.1498	0.9382	0.9686
No log	21.0	42	1.0354	0.0364	1.0352	1.0174
No log	22.0	44	1.0102	0.0837	1.0101	1.0051
No log	23.0	46	0.8305	0.3513	0.8305	0.9113
No log	24.0	48	0.7451	0.3567	0.7454	0.8633
No log	25.0	50	0.7795	0.3756	0.7799	0.8831
No log	26.0	52	0.9587	0.3219	0.9590	0.9793
No log	27.0	54	0.8217	0.3836	0.8222	0.9068
No log	28.0	56	0.8433	0.3832	0.8439	0.9186
No log	29.0	58	1.1604	0.2812	1.1608	1.0774
No log	30.0	60	0.8870	0.3952	0.8877	0.9422
No log	31.0	62	0.7089	0.4222	0.7098	0.8425
No log	32.0	64	0.7638	0.4374	0.7647	0.8745
No log	33.0	66	0.8383	0.4065	0.8393	0.9161
No log	34.0	68	0.7391	0.4247	0.7403	0.8604
No log	35.0	70	0.7535	0.4821	0.7547	0.8688
No log	36.0	72	0.8805	0.4597	0.8817	0.9390
No log	37.0	74	0.8788	0.4392	0.8800	0.9381
No log	38.0	76	0.7334	0.5079	0.7346	0.8571
No log	39.0	78	0.7711	0.5211	0.7723	0.8788
No log	40.0	80	1.2843	0.3470	1.2852	1.1337
No log	41.0	82	1.5276	0.2904	1.5284	1.2363
No log	42.0	84	1.0466	0.4336	1.0476	1.0235
No log	43.0	86	0.7729	0.5532	0.7740	0.8798
No log	44.0	88	0.7764	0.5358	0.7773	0.8817
No log	45.0	90	0.7175	0.5633	0.7184	0.8476
No log	46.0	92	0.9302	0.4815	0.9312	0.9650
No log	47.0	94	1.3240	0.3544	1.3250	1.1511
No log	48.0	96	1.4479	0.3267	1.4488	1.2037
No log	49.0	98	1.1894	0.3789	1.1904	1.0911
No log	50.0	100	0.8166	0.5207	0.8177	0.9043
No log	51.0	102	0.7590	0.5412	0.7601	0.8718
No log	52.0	104	0.7885	0.5157	0.7895	0.8886
No log	53.0	106	0.7975	0.4818	0.7985	0.8936
No log	54.0	108	0.7211	0.5264	0.7221	0.8498
No log	55.0	110	0.7200	0.5401	0.7210	0.8491
No log	56.0	112	0.7765	0.4942	0.7776	0.8818
No log	57.0	114	0.8023	0.4987	0.8033	0.8963
No log	58.0	116	0.8007	0.5152	0.8017	0.8954
No log	59.0	118	0.8060	0.5014	0.8069	0.8983
No log	60.0	120	0.8725	0.4931	0.8734	0.9346

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_sp010_lw050_fold3

BERT_AugV8_k1_task1_organization_sp010_lw050_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp010_lw050_fold3