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	10.0731	0.0036	10.0717	3.1736
No log	2.0	4	7.8764	0.0	7.8749	2.8062
No log	3.0	6	6.7406	0.0	6.7394	2.5960
No log	4.0	8	5.3743	0.0086	5.3728	2.3179
No log	5.0	10	3.8978	0.0038	3.8968	1.9740
No log	6.0	12	3.0128	0.0	3.0117	1.7354
No log	7.0	14	2.3504	0.1628	2.3496	1.5328
No log	8.0	16	1.8693	0.0599	1.8684	1.3669
No log	9.0	18	1.4875	0.0549	1.4870	1.2194
No log	10.0	20	1.1632	0.0302	1.1627	1.0783
No log	11.0	22	0.9613	0.0687	0.9610	0.9803
No log	12.0	24	0.7946	0.3986	0.7943	0.8912
No log	13.0	26	0.7237	0.4328	0.7234	0.8506
No log	14.0	28	0.6917	0.3420	0.6915	0.8316
No log	15.0	30	0.5807	0.4523	0.5806	0.7620
No log	16.0	32	0.8603	0.3897	0.8602	0.9274
No log	17.0	34	0.5897	0.5230	0.5896	0.7679
No log	18.0	36	0.6200	0.4456	0.6201	0.7875
No log	19.0	38	0.5118	0.5275	0.5118	0.7154
No log	20.0	40	0.9967	0.4060	0.9967	0.9983
No log	21.0	42	0.7015	0.5069	0.7015	0.8376
No log	22.0	44	0.5205	0.5102	0.5206	0.7215
No log	23.0	46	0.5888	0.5505	0.5889	0.7674
No log	24.0	48	1.0074	0.4349	1.0076	1.0038
No log	25.0	50	0.7219	0.5267	0.7222	0.8498
No log	26.0	52	0.5343	0.6038	0.5346	0.7312
No log	27.0	54	0.5866	0.5747	0.5869	0.7661
No log	28.0	56	0.9726	0.4382	0.9729	0.9863
No log	29.0	58	0.6621	0.5299	0.6624	0.8139
No log	30.0	60	0.5907	0.5664	0.5911	0.7688
No log	31.0	62	0.5626	0.5492	0.5631	0.7504
No log	32.0	64	0.8054	0.4775	0.8057	0.8976
No log	33.0	66	0.7343	0.4884	0.7347	0.8572
No log	34.0	68	0.5656	0.5417	0.5660	0.7524
No log	35.0	70	0.6101	0.5782	0.6106	0.7814
No log	36.0	72	0.6254	0.5550	0.6259	0.7911
No log	37.0	74	0.6842	0.5126	0.6847	0.8274
No log	38.0	76	0.5890	0.5403	0.5895	0.7678
No log	39.0	78	0.6004	0.5487	0.6009	0.7752
No log	40.0	80	0.5939	0.5331	0.5944	0.7710
No log	41.0	82	0.6532	0.5154	0.6537	0.8085
No log	42.0	84	0.5923	0.5323	0.5928	0.7699
No log	43.0	86	0.5910	0.5438	0.5915	0.7691
No log	44.0	88	0.6598	0.5211	0.6603	0.8126
No log	45.0	90	0.5896	0.5483	0.5900	0.7681
No log	46.0	92	0.5998	0.5160	0.6003	0.7748
No log	47.0	94	0.6744	0.5362	0.6748	0.8215
No log	48.0	96	0.6364	0.5516	0.6368	0.7980
No log	49.0	98	0.5872	0.5431	0.5876	0.7666
No log	50.0	100	0.5922	0.5259	0.5926	0.7698
No log	51.0	102	0.6572	0.5190	0.6575	0.8109
No log	52.0	104	0.5734	0.4847	0.5737	0.7575
No log	53.0	106	0.5828	0.5350	0.5832	0.7636
No log	54.0	108	0.5650	0.5488	0.5654	0.7520
No log	55.0	110	0.6415	0.5392	0.6419	0.8012
No log	56.0	112	0.6365	0.5375	0.6370	0.7981

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold3

BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold3