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	3	6.4536	0.0	6.4513	2.5399
No log	2.0	6	4.0081	0.0079	4.0061	2.0015
No log	3.0	9	2.8658	0.0	2.8641	1.6924
No log	4.0	12	1.9506	0.0315	1.9490	1.3961
No log	5.0	15	1.4039	0.0	1.4024	1.1842
No log	6.0	18	1.0399	0.0	1.0385	1.0191
No log	7.0	21	0.9361	0.1152	0.9349	0.9669
No log	8.0	24	0.7770	0.2327	0.7760	0.8809
No log	9.0	27	0.7286	0.2241	0.7278	0.8531
No log	10.0	30	0.5404	0.5721	0.5396	0.7346
No log	11.0	33	0.4745	0.5583	0.4738	0.6883
No log	12.0	36	0.5674	0.5931	0.5665	0.7527
No log	13.0	39	0.6021	0.4227	0.6013	0.7755
No log	14.0	42	0.6259	0.5169	0.6248	0.7905
No log	15.0	45	0.8056	0.4408	0.8049	0.8972
No log	16.0	48	0.5909	0.4469	0.5902	0.7682
No log	17.0	51	0.7156	0.4746	0.7145	0.8453
No log	18.0	54	0.8485	0.4559	0.8481	0.9209
No log	19.0	57	0.5747	0.5334	0.5741	0.7577
No log	20.0	60	0.6022	0.5603	0.6017	0.7757
No log	21.0	63	0.6215	0.5691	0.6211	0.7881
No log	22.0	66	0.5561	0.5985	0.5556	0.7454
No log	23.0	69	0.5608	0.5840	0.5603	0.7485
No log	24.0	72	0.5742	0.6008	0.5737	0.7575
No log	25.0	75	0.5543	0.5805	0.5537	0.7441
No log	26.0	78	0.8299	0.5216	0.8297	0.9109
No log	27.0	81	0.5223	0.5757	0.5217	0.7223
No log	28.0	84	0.5224	0.5601	0.5218	0.7224
No log	29.0	87	0.6398	0.5697	0.6395	0.7997
No log	30.0	90	0.5375	0.5515	0.5370	0.7328
No log	31.0	93	0.6591	0.5708	0.6588	0.8117
No log	32.0	96	0.5665	0.5734	0.5659	0.7523
No log	33.0	99	0.5521	0.5757	0.5516	0.7427
No log	34.0	102	0.5778	0.5640	0.5773	0.7598
No log	35.0	105	0.5491	0.5750	0.5486	0.7407
No log	36.0	108	0.5850	0.5481	0.5845	0.7645
No log	37.0	111	0.5578	0.5401	0.5572	0.7464
No log	38.0	114	0.5972	0.5403	0.5968	0.7725
No log	39.0	117	0.5573	0.5821	0.5568	0.7462
No log	40.0	120	0.5492	0.5960	0.5486	0.7407
No log	41.0	123	0.5987	0.5715	0.5983	0.7735
No log	42.0	126	0.5390	0.5895	0.5384	0.7338
No log	43.0	129	0.5410	0.5878	0.5405	0.7352
No log	44.0	132	0.5436	0.5608	0.5430	0.7369
No log	45.0	135	0.5743	0.5532	0.5737	0.7574
No log	46.0	138	0.5684	0.5655	0.5677	0.7534
No log	47.0	141	0.5580	0.5622	0.5573	0.7465
No log	48.0	144	0.5597	0.5649	0.5590	0.7477
No log	49.0	147	0.5613	0.5799	0.5606	0.7488
No log	50.0	150	0.5573	0.5633	0.5566	0.7461
No log	51.0	153	0.5765	0.5651	0.5759	0.7589
No log	52.0	156	0.5532	0.5212	0.5525	0.7433
No log	53.0	159	0.5589	0.5355	0.5583	0.7472
No log	54.0	162	0.5678	0.5464	0.5671	0.7531

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_k5_k5_fold1

BERT_V8_sp10_lw40_ex50_lo50_k5_k5_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_k5_k5_fold1