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	13.0092	0.0	13.0073	3.6066
No log	2.0	4	10.6292	0.0076	10.6273	3.2600
No log	3.0	6	8.0641	0.0	8.0627	2.8395
No log	4.0	8	5.7292	0.0311	5.7282	2.3934
No log	5.0	10	6.1022	-0.0031	6.1006	2.4699
No log	6.0	12	4.0725	0.0062	4.0713	2.0177
No log	7.0	14	3.2092	0.0003	3.2081	1.7911
No log	8.0	16	2.3263	0.0568	2.3256	1.5250
No log	9.0	18	1.8969	0.0462	1.8961	1.3770
No log	10.0	20	1.5918	0.0427	1.5914	1.2615
No log	11.0	22	1.1228	0.0202	1.1225	1.0595
No log	12.0	24	1.0413	0.0102	1.0408	1.0202
No log	13.0	26	0.8110	0.3971	0.8107	0.9004
No log	14.0	28	0.8336	0.3258	0.8333	0.9128
No log	15.0	30	0.7222	0.3991	0.7220	0.8497
No log	16.0	32	0.6698	0.3616	0.6696	0.8183
No log	17.0	34	0.7468	0.4032	0.7465	0.8640
No log	18.0	36	0.8023	0.2849	0.8020	0.8956
No log	19.0	38	0.6013	0.4401	0.6011	0.7753
No log	20.0	40	0.6049	0.4374	0.6048	0.7777
No log	21.0	42	0.6819	0.4279	0.6818	0.8257
No log	22.0	44	0.5424	0.5009	0.5424	0.7365
No log	23.0	46	0.5092	0.5110	0.5093	0.7136
No log	24.0	48	0.5273	0.5582	0.5274	0.7262
No log	25.0	50	0.5254	0.6321	0.5255	0.7249
No log	26.0	52	0.5645	0.5991	0.5647	0.7514
No log	27.0	54	0.6790	0.5294	0.6791	0.8241
No log	28.0	56	0.5481	0.6350	0.5481	0.7404
No log	29.0	58	0.5856	0.6202	0.5855	0.7652
No log	30.0	60	0.5288	0.6531	0.5288	0.7272
No log	31.0	62	0.6021	0.6071	0.6021	0.7760
No log	32.0	64	0.5413	0.6388	0.5413	0.7357
No log	33.0	66	0.5371	0.6426	0.5370	0.7328
No log	34.0	68	0.6141	0.5862	0.6141	0.7837
No log	35.0	70	0.5421	0.6320	0.5422	0.7363
No log	36.0	72	0.5174	0.6305	0.5174	0.7193
No log	37.0	74	0.5579	0.6258	0.5580	0.7470
No log	38.0	76	0.5756	0.6118	0.5756	0.7587
No log	39.0	78	0.4987	0.6333	0.4986	0.7061
No log	40.0	80	0.4956	0.6270	0.4955	0.7039
No log	41.0	82	0.5242	0.6558	0.5241	0.7240
No log	42.0	84	0.5311	0.6510	0.5311	0.7288
No log	43.0	86	0.5181	0.6338	0.5180	0.7197
No log	44.0	88	0.5362	0.6403	0.5362	0.7323
No log	45.0	90	0.5664	0.6190	0.5664	0.7526
No log	46.0	92	0.5537	0.6358	0.5537	0.7441
No log	47.0	94	0.5426	0.6296	0.5426	0.7366
No log	48.0	96	0.6354	0.5706	0.6354	0.7971
No log	49.0	98	0.5795	0.5905	0.5794	0.7612
No log	50.0	100	0.5730	0.6223	0.5729	0.7569
No log	51.0	102	0.5391	0.6167	0.5390	0.7342
No log	52.0	104	0.5663	0.6302	0.5662	0.7525
No log	53.0	106	0.6536	0.5641	0.6535	0.8084
No log	54.0	108	0.6446	0.5701	0.6445	0.8028
No log	55.0	110	0.5259	0.6153	0.5259	0.7252
No log	56.0	112	0.5188	0.6205	0.5188	0.7203
No log	57.0	114	0.5781	0.6103	0.5781	0.7603
No log	58.0	116	0.6486	0.5653	0.6486	0.8054
No log	59.0	118	0.5690	0.6203	0.5690	0.7543
No log	60.0	120	0.5385	0.6330	0.5384	0.7338
No log	61.0	122	0.5648	0.6067	0.5647	0.7515
No log	62.0	124	0.5267	0.6250	0.5267	0.7257
No log	63.0	126	0.5455	0.6238	0.5455	0.7386
No log	64.0	128	0.6166	0.5761	0.6165	0.7852
No log	65.0	130	0.6083	0.5811	0.6082	0.7799
No log	66.0	132	0.5483	0.6165	0.5483	0.7405
No log	67.0	134	0.5469	0.6252	0.5468	0.7395
No log	68.0	136	0.6266	0.5681	0.6265	0.7915
No log	69.0	138	0.6504	0.5552	0.6504	0.8065
No log	70.0	140	0.5755	0.5950	0.5755	0.7586
No log	71.0	142	0.5526	0.6392	0.5526	0.7434

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_lo100_k3_k3_fold3

BERT_V8_sp10_lw20_ex200_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_ex200_lo100_k3_k3_fold3