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	8.9521	0.0	8.9521	2.9920
No log	2.0	4	7.8399	0.0	7.8399	2.8000
No log	3.0	6	7.1996	0.0	7.1996	2.6832
No log	4.0	8	6.4610	-0.0009	6.4610	2.5418
No log	5.0	10	5.7265	0.0112	5.7265	2.3930
No log	6.0	12	5.1181	0.0115	5.1181	2.2623
No log	7.0	14	4.4134	0.0039	4.4134	2.1008
No log	8.0	16	3.9510	0.0039	3.9510	1.9877
No log	9.0	18	3.2196	0.0	3.2196	1.7943
No log	10.0	20	2.7152	0.0	2.7152	1.6478
No log	11.0	22	2.1944	0.0419	2.1944	1.4813
No log	12.0	24	1.7381	0.0316	1.7381	1.3184
No log	13.0	26	1.4404	0.0316	1.4404	1.2002
No log	14.0	28	1.2031	0.0212	1.2031	1.0968
No log	15.0	30	1.0249	0.0316	1.0249	1.0124
No log	16.0	32	1.0721	0.0419	1.0721	1.0354
No log	17.0	34	1.2130	0.0484	1.2130	1.1014
No log	18.0	36	0.9186	0.0810	0.9186	0.9584
No log	19.0	38	0.8139	0.2054	0.8139	0.9021
No log	20.0	40	0.8652	0.0683	0.8652	0.9302
No log	21.0	42	0.7358	0.2207	0.7358	0.8578
No log	22.0	44	0.6488	0.4102	0.6488	0.8055
No log	23.0	46	0.9167	0.2553	0.9167	0.9575
No log	24.0	48	0.7360	0.4370	0.7360	0.8579
No log	25.0	50	0.5167	0.4770	0.5167	0.7188
No log	26.0	52	0.4937	0.4715	0.4937	0.7027
No log	27.0	54	0.4989	0.5185	0.4989	0.7064
No log	28.0	56	1.1600	0.3145	1.1600	1.0770
No log	29.0	58	2.0006	0.2211	2.0006	1.4144
No log	30.0	60	2.0447	0.2193	2.0447	1.4299
No log	31.0	62	1.3065	0.1842	1.3065	1.1430
No log	32.0	64	0.6616	0.4612	0.6616	0.8134
No log	33.0	66	0.4819	0.4648	0.4819	0.6942
No log	34.0	68	0.5086	0.5276	0.5086	0.7132
No log	35.0	70	0.6969	0.4788	0.6969	0.8348
No log	36.0	72	0.6500	0.4828	0.6500	0.8062
No log	37.0	74	0.4944	0.5125	0.4944	0.7031
No log	38.0	76	0.5173	0.4899	0.5173	0.7193
No log	39.0	78	0.7750	0.4676	0.7750	0.8803
No log	40.0	80	0.8431	0.4641	0.8431	0.9182
No log	41.0	82	0.6474	0.4833	0.6474	0.8046
No log	42.0	84	0.5875	0.4631	0.5875	0.7665
No log	43.0	86	0.6083	0.4718	0.6083	0.7800
No log	44.0	88	0.6138	0.4736	0.6138	0.7834
No log	45.0	90	1.0506	0.4172	1.0506	1.0250
No log	46.0	92	0.8327	0.4671	0.8327	0.9126
No log	47.0	94	0.6258	0.5585	0.6258	0.7911
No log	48.0	96	0.7595	0.5079	0.7595	0.8715
No log	49.0	98	0.7490	0.4988	0.7490	0.8654
No log	50.0	100	0.5914	0.4938	0.5914	0.7690
No log	51.0	102	0.8380	0.4219	0.8380	0.9154
No log	52.0	104	0.9004	0.4166	0.9004	0.9489
No log	53.0	106	0.6768	0.4393	0.6768	0.8227
No log	54.0	108	0.6702	0.5110	0.6702	0.8187
No log	55.0	110	0.6930	0.4760	0.6930	0.8325
No log	56.0	112	0.6932	0.4807	0.6932	0.8326
No log	57.0	114	0.6765	0.4969	0.6765	0.8225
No log	58.0	116	0.7189	0.4964	0.7189	0.8479
No log	59.0	118	0.8593	0.4243	0.8593	0.9270
No log	60.0	120	0.8129	0.4634	0.8129	0.9016
No log	61.0	122	0.6309	0.5023	0.6309	0.7943
No log	62.0	124	0.6274	0.5055	0.6274	0.7921

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw010_fold0

Trial3BERT_AugV8_k1_task1_organization_sp020_lw010_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Trial3BERT_AugV8_k1_task1_organization_sp020_lw010_fold0