learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	7.6515	0.0	7.6492	2.7657
No log	2.0	4	7.2604	0.0	7.2581	2.6941
No log	3.0	6	6.6180	0.0	6.6158	2.5721
No log	4.0	8	5.3839	-0.0131	5.3819	2.3199
No log	5.0	10	4.1816	0.0	4.1795	2.0444
No log	6.0	12	3.3117	0.0	3.3097	1.8193
No log	7.0	14	2.5437	0.0	2.5420	1.5944
No log	8.0	16	1.9512	0.0645	1.9495	1.3963
No log	9.0	18	1.5546	0.0211	1.5531	1.2462
No log	10.0	20	1.2505	0.0	1.2490	1.1176
No log	11.0	22	1.0495	0.0	1.0481	1.0238
No log	12.0	24	0.9373	0.0	0.9360	0.9675
No log	13.0	26	0.8444	0.3069	0.8432	0.9183
No log	14.0	28	0.7818	0.2446	0.7807	0.8836
No log	15.0	30	0.6906	0.3398	0.6897	0.8305
No log	16.0	32	0.8725	0.2255	0.8714	0.9335
No log	17.0	34	0.7393	0.3427	0.7383	0.8593
No log	18.0	36	0.6456	0.4903	0.6447	0.8030
No log	19.0	38	0.5972	0.5306	0.5964	0.7723
No log	20.0	40	0.6241	0.3967	0.6233	0.7895
No log	21.0	42	0.6082	0.4253	0.6074	0.7794
No log	22.0	44	0.5812	0.5626	0.5804	0.7618
No log	23.0	46	0.6714	0.5680	0.6706	0.8189
No log	24.0	48	0.4739	0.5490	0.4731	0.6878
No log	25.0	50	0.5180	0.5103	0.5172	0.7192
No log	26.0	52	0.5498	0.5795	0.5489	0.7409
No log	27.0	54	0.5799	0.5851	0.5790	0.7609
No log	28.0	56	0.4841	0.5400	0.4832	0.6951
No log	29.0	58	0.5837	0.4843	0.5829	0.7635
No log	30.0	60	0.5404	0.5148	0.5396	0.7346
No log	31.0	62	0.4938	0.5625	0.4930	0.7021
No log	32.0	64	0.5099	0.6038	0.5093	0.7136
No log	33.0	66	0.6422	0.5813	0.6416	0.8010
No log	34.0	68	0.4865	0.6511	0.4860	0.6972
No log	35.0	70	0.4862	0.6741	0.4857	0.6970
No log	36.0	72	0.4878	0.6634	0.4874	0.6981
No log	37.0	74	0.4980	0.6667	0.4975	0.7053
No log	38.0	76	0.4810	0.6569	0.4805	0.6932
No log	39.0	78	0.5480	0.5754	0.5472	0.7397
No log	40.0	80	0.5823	0.5561	0.5815	0.7626
No log	41.0	82	0.5469	0.5734	0.5461	0.7390
No log	42.0	84	0.4820	0.6131	0.4812	0.6937
No log	43.0	86	0.4891	0.6231	0.4885	0.6989
No log	44.0	88	0.5023	0.6123	0.5016	0.7083
No log	45.0	90	0.5295	0.6258	0.5288	0.7272
No log	46.0	92	0.5997	0.5894	0.5991	0.7740
No log	47.0	94	0.5581	0.5967	0.5575	0.7466
No log	48.0	96	0.5917	0.5706	0.5909	0.7687
No log	49.0	98	0.5934	0.5756	0.5927	0.7698
No log	50.0	100	0.5316	0.6088	0.5310	0.7287
No log	51.0	102	0.5498	0.5986	0.5491	0.7410
No log	52.0	104	0.5961	0.5850	0.5953	0.7715
No log	53.0	106	0.6112	0.5802	0.6103	0.7812
No log	54.0	108	0.5362	0.6060	0.5355	0.7318
No log	55.0	110	0.5969	0.5910	0.5963	0.7722
No log	56.0	112	0.5527	0.6012	0.5520	0.7430
No log	57.0	114	0.5307	0.5982	0.5299	0.7280
No log	58.0	116	0.5171	0.5907	0.5164	0.7186
No log	59.0	118	0.5004	0.6131	0.4998	0.7069
No log	60.0	120	0.5098	0.5932	0.5092	0.7136
No log	61.0	122	0.4910	0.6149	0.4903	0.7002
No log	62.0	124	0.5223	0.6135	0.5215	0.7222
No log	63.0	126	0.4927	0.6308	0.4920	0.7014
No log	64.0	128	0.5097	0.6205	0.5091	0.7135
No log	65.0	130	0.5107	0.6201	0.5101	0.7142

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1

BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1