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	11.0221	0.0208	11.0225	3.3200
No log	2.0	4	10.3698	0.0	10.3700	3.2202
No log	3.0	6	9.5887	0.0	9.5889	3.0966
No log	4.0	8	8.2632	0.0	8.2634	2.8746
No log	5.0	10	7.3129	0.0	7.3132	2.7043
No log	6.0	12	6.7664	0.0	6.7667	2.6013
No log	7.0	14	5.8477	0.0259	5.8479	2.4183
No log	8.0	16	4.8607	0.0	4.8610	2.2048
No log	9.0	18	3.9326	0.0	3.9330	1.9832
No log	10.0	20	3.0840	0.0	3.0844	1.7563
No log	11.0	22	2.5299	0.0	2.5304	1.5907
No log	12.0	24	2.1469	0.1280	2.1473	1.4654
No log	13.0	26	1.7108	0.0280	1.7112	1.3081
No log	14.0	28	1.5264	0.0107	1.5268	1.2356
No log	15.0	30	1.2108	0.0107	1.2112	1.1006
No log	16.0	32	0.9983	0.0107	0.9987	0.9993
No log	17.0	34	0.8722	0.0935	0.8726	0.9341
No log	18.0	36	0.8163	0.3667	0.8166	0.9037
No log	19.0	38	0.7740	0.3967	0.7743	0.8799
No log	20.0	40	0.8575	0.1964	0.8577	0.9261
No log	21.0	42	0.7472	0.4704	0.7474	0.8645
No log	22.0	44	0.7860	0.2674	0.7861	0.8866
No log	23.0	46	1.0216	0.0736	1.0219	1.0109
No log	24.0	48	0.9556	0.1024	0.9559	0.9777
No log	25.0	50	0.8289	0.3892	0.8291	0.9105
No log	26.0	52	1.2268	0.2676	1.2274	1.1079
No log	27.0	54	0.9232	0.4500	0.9236	0.9610
No log	28.0	56	0.5835	0.5358	0.5836	0.7639
No log	29.0	58	0.6930	0.5284	0.6932	0.8326
No log	30.0	60	0.9994	0.3905	0.9998	0.9999
No log	31.0	62	1.1501	0.2722	1.1504	1.0726
No log	32.0	64	1.0133	0.3322	1.0136	1.0068
No log	33.0	66	0.7194	0.5007	0.7195	0.8483
No log	34.0	68	0.6912	0.5120	0.6914	0.8315
No log	35.0	70	0.9197	0.3815	0.9199	0.9591
No log	36.0	72	0.8369	0.4494	0.8369	0.9148
No log	37.0	74	0.5122	0.5260	0.5120	0.7155
No log	38.0	76	0.5128	0.5027	0.5125	0.7159
No log	39.0	78	0.9238	0.4267	0.9233	0.9609
No log	40.0	80	1.1332	0.3727	1.1328	1.0643
No log	41.0	82	0.5399	0.5507	0.5394	0.7345
No log	42.0	84	0.5207	0.5473	0.5203	0.7213
No log	43.0	86	1.1264	0.3409	1.1260	1.0611
No log	44.0	88	1.3429	0.3022	1.3426	1.1587
No log	45.0	90	0.6611	0.5046	0.6606	0.8128
No log	46.0	92	0.5259	0.5623	0.5253	0.7248
No log	47.0	94	0.5805	0.5570	0.5798	0.7614
No log	48.0	96	1.4691	0.2995	1.4685	1.2118
No log	49.0	98	1.9205	0.2202	1.9199	1.3856
No log	50.0	100	1.0218	0.3932	1.0210	1.0105
No log	51.0	102	0.6086	0.5540	0.6077	0.7796
No log	52.0	104	0.6215	0.5581	0.6207	0.7878
No log	53.0	106	1.2996	0.3141	1.2990	1.1397
No log	54.0	108	1.5717	0.2760	1.5711	1.2535
No log	55.0	110	0.9137	0.3993	0.9129	0.9555
No log	56.0	112	0.6247	0.5634	0.6239	0.7899
No log	57.0	114	0.6271	0.5564	0.6264	0.7914
No log	58.0	116	0.9564	0.4057	0.9558	0.9777
No log	59.0	118	0.8579	0.4331	0.8574	0.9260
No log	60.0	120	0.6251	0.5386	0.6245	0.7903
No log	61.0	122	0.6340	0.5399	0.6334	0.7958
No log	62.0	124	0.7648	0.5108	0.7642	0.8742
No log	63.0	126	0.9353	0.4100	0.9347	0.9668
No log	64.0	128	0.7750	0.5036	0.7744	0.8800
No log	65.0	130	0.6316	0.5710	0.6309	0.7943
No log	66.0	132	0.6136	0.5543	0.6129	0.7829
No log	67.0	134	0.8681	0.4533	0.8674	0.9314
No log	68.0	136	1.1038	0.3580	1.1031	1.0503
No log	69.0	138	0.8156	0.4752	0.8149	0.9027
No log	70.0	140	0.5863	0.5437	0.5857	0.7653
No log	71.0	142	0.6456	0.5531	0.6450	0.8031
No log	72.0	144	1.0120	0.3700	1.0114	1.0057
No log	73.0	146	1.0466	0.3751	1.0459	1.0227
No log	74.0	148	0.7174	0.5236	0.7168	0.8466
No log	75.0	150	0.6235	0.5353	0.6228	0.7892
No log	76.0	152	0.6342	0.5322	0.6334	0.7959
No log	77.0	154	0.7380	0.5306	0.7373	0.8586
No log	78.0	156	1.1913	0.3144	1.1907	1.0912
No log	79.0	158	1.2154	0.3125	1.2149	1.1022
No log	80.0	160	0.8261	0.4469	0.8257	0.9087

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_sp030_lw040_fold2

BERT_AugV8_k1_task1_organization_sp030_lw040_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp030_lw040_fold2