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	10.3653	-0.0004	10.3628	3.2191
No log	2.0	4	8.9331	0.0	8.9306	2.9884
No log	3.0	6	7.6900	0.0	7.6875	2.7726
No log	4.0	8	6.3512	0.0052	6.3491	2.5197
No log	5.0	10	5.2236	0.0394	5.2215	2.2851
No log	6.0	12	4.1784	0.0064	4.1764	2.0436
No log	7.0	14	3.5017	0.0	3.5001	1.8709
No log	8.0	16	2.1581	0.1935	2.1566	1.4685
No log	9.0	18	1.5873	0.0828	1.5858	1.2593
No log	10.0	20	1.2060	0.0315	1.2046	1.0975
No log	11.0	22	0.9641	0.0	0.9628	0.9812
No log	12.0	24	0.8316	0.3669	0.8304	0.9113
No log	13.0	26	0.7831	0.2479	0.7820	0.8843
No log	14.0	28	0.7265	0.3056	0.7254	0.8517
No log	15.0	30	0.6692	0.3527	0.6681	0.8174
No log	16.0	32	0.6037	0.4276	0.6026	0.7763
No log	17.0	34	0.5795	0.5095	0.5783	0.7605
No log	18.0	36	0.5543	0.5160	0.5532	0.7438
No log	19.0	38	0.8856	0.4205	0.8840	0.9402
No log	20.0	40	0.6300	0.5071	0.6287	0.7929
No log	21.0	42	0.7263	0.5142	0.7248	0.8514
No log	22.0	44	0.6503	0.5105	0.6489	0.8056
No log	23.0	46	0.7721	0.4915	0.7706	0.8778
No log	24.0	48	0.6566	0.5566	0.6555	0.8096
No log	25.0	50	0.9109	0.4268	0.9092	0.9535
No log	26.0	52	0.7645	0.5024	0.7630	0.8735
No log	27.0	54	1.1579	0.3385	1.1560	1.0752
No log	28.0	56	0.9555	0.4169	0.9537	0.9766
No log	29.0	58	0.6773	0.5305	0.6760	0.8222
No log	30.0	60	0.8246	0.4362	0.8230	0.9072
No log	31.0	62	0.8195	0.4452	0.8178	0.9043
No log	32.0	64	0.7174	0.4841	0.7160	0.8462
No log	33.0	66	0.9061	0.4106	0.9043	0.9509
No log	34.0	68	0.8832	0.4175	0.8814	0.9388
No log	35.0	70	0.7697	0.4548	0.7681	0.8764
No log	36.0	72	0.9761	0.3912	0.9742	0.9870
No log	37.0	74	0.9361	0.4093	0.9342	0.9666
No log	38.0	76	0.7655	0.4443	0.7638	0.8740
No log	39.0	78	0.8872	0.4267	0.8853	0.9409
No log	40.0	80	0.8293	0.4094	0.8275	0.9097
No log	41.0	82	0.7300	0.4597	0.7284	0.8535
No log	42.0	84	0.8325	0.4298	0.8307	0.9114
No log	43.0	86	0.8159	0.4392	0.8142	0.9023
No log	44.0	88	0.7319	0.4575	0.7302	0.8545
No log	45.0	90	0.9224	0.4279	0.9206	0.9595
No log	46.0	92	0.9272	0.4332	0.9254	0.9620
No log	47.0	94	0.7020	0.4827	0.7005	0.8370
No log	48.0	96	0.6941	0.4792	0.6926	0.8322
No log	49.0	98	0.8438	0.4491	0.8420	0.9176
No log	50.0	100	0.9115	0.4310	0.9097	0.9538
No log	51.0	102	0.7514	0.4656	0.7497	0.8659
No log	52.0	104	0.7735	0.4626	0.7718	0.8785
No log	53.0	106	0.8981	0.4352	0.8962	0.9467
No log	54.0	108	0.8131	0.4525	0.8114	0.9008

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k3_k3_fold1

BERT_V8_sp10_lw20_ex200_lo50_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_ex200_lo50_k3_k3_fold1