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	10.9133	0.0072	10.9105	3.3031
No log	2.0	4	8.4476	0.0	8.4452	2.9061
No log	3.0	6	6.5745	0.0	6.5723	2.5637
No log	4.0	8	4.8298	0.0118	4.8279	2.1972
No log	5.0	10	3.7470	0.0040	3.7451	1.9352
No log	6.0	12	2.8160	0.0	2.8141	1.6775
No log	7.0	14	2.1794	0.0744	2.1777	1.4757
No log	8.0	16	1.5637	0.0315	1.5622	1.2499
No log	9.0	18	1.3661	0.0	1.3646	1.1682
No log	10.0	20	1.0863	0.0	1.0849	1.0416
No log	11.0	22	0.9143	0.1742	0.9130	0.9555
No log	12.0	24	0.8799	0.1847	0.8787	0.9374
No log	13.0	26	nan	0.1562	nan	nan
No log	14.0	28	0.6599	0.4408	0.6588	0.8117
No log	15.0	30	0.6778	0.3514	0.6767	0.8226
No log	16.0	32	0.5734	0.5468	0.5723	0.7565
No log	17.0	34	0.5350	0.5244	0.5340	0.7307
No log	18.0	36	0.5456	0.4901	0.5446	0.7379
No log	19.0	38	0.5172	0.5007	0.5162	0.7185
No log	20.0	40	0.5231	0.5369	0.5221	0.7226
No log	21.0	42	0.5344	0.5346	0.5333	0.7303
No log	22.0	44	0.6842	0.4728	0.6833	0.8266
No log	23.0	46	0.5182	0.6250	0.5173	0.7192
No log	24.0	48	0.5160	0.6462	0.5152	0.7178
No log	25.0	50	0.7368	0.5583	0.7361	0.8580
No log	26.0	52	0.4942	0.6275	0.4934	0.7024
No log	27.0	54	0.5082	0.6018	0.5073	0.7122
No log	28.0	56	0.8888	0.4806	0.8881	0.9424
No log	29.0	58	1.0064	0.4431	1.0057	1.0029
No log	30.0	60	0.5870	0.5545	0.5861	0.7656
No log	31.0	62	0.5354	0.5484	0.5344	0.7311
No log	32.0	64	0.5369	0.6132	0.5362	0.7323
No log	33.0	66	0.5859	0.6095	0.5852	0.7650
No log	34.0	68	0.5117	0.6150	0.5109	0.7148
No log	35.0	70	0.5583	0.6130	0.5576	0.7467
No log	36.0	72	0.6129	0.5751	0.6121	0.7824
No log	37.0	74	0.5524	0.6014	0.5516	0.7427
No log	38.0	76	0.6098	0.5783	0.6090	0.7804
No log	39.0	78	0.6081	0.5700	0.6072	0.7792
No log	40.0	80	0.5540	0.5968	0.5531	0.7437
No log	41.0	82	0.5585	0.6012	0.5577	0.7468
No log	42.0	84	0.5669	0.5910	0.5660	0.7523
No log	43.0	86	0.6869	0.5310	0.6860	0.8283
No log	44.0	88	0.6712	0.5332	0.6702	0.8187
No log	45.0	90	0.6163	0.5649	0.6154	0.7845
No log	46.0	92	0.5930	0.5816	0.5921	0.7695
No log	47.0	94	0.5918	0.5630	0.5909	0.7687
No log	48.0	96	0.5592	0.5656	0.5583	0.7472
No log	49.0	98	0.5759	0.5676	0.5750	0.7583
No log	50.0	100	0.5778	0.5706	0.5769	0.7595
No log	51.0	102	0.5645	0.5895	0.5636	0.7507
No log	52.0	104	0.6150	0.5692	0.6141	0.7837
No log	53.0	106	0.5909	0.5522	0.5898	0.7680
No log	54.0	108	0.6190	0.5357	0.6180	0.7861

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_fold1

BERT_V8_sp10_lw20_ex100_lo100_k3_k3_fold1

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_fold1