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	3	9.9626	0.0058	9.9626	3.1564
No log	2.0	6	6.7478	0.0	6.7478	2.5976
No log	3.0	9	4.4476	0.0171	4.4476	2.1089
No log	4.0	12	2.7613	0.0017	2.7613	1.6617
No log	5.0	15	1.7925	0.1058	1.7925	1.3388
No log	6.0	18	1.3271	0.0445	1.3271	1.1520
No log	7.0	21	0.8937	0.1101	0.8937	0.9453
No log	8.0	24	1.1438	0.0420	1.1438	1.0695
No log	9.0	27	0.8025	0.3116	0.8025	0.8958
No log	10.0	30	0.6916	0.3247	0.6916	0.8316
No log	11.0	33	0.7668	0.3417	0.7668	0.8757
No log	12.0	36	0.6498	0.4704	0.6498	0.8061
No log	13.0	39	0.6564	0.4719	0.6564	0.8102
No log	14.0	42	0.7259	0.4269	0.7259	0.8520
No log	15.0	45	0.7218	0.4043	0.7218	0.8496
No log	16.0	48	0.8552	0.3535	0.8552	0.9248
No log	17.0	51	0.7304	0.4696	0.7304	0.8546
No log	18.0	54	0.6908	0.5048	0.6908	0.8311
No log	19.0	57	0.7224	0.4435	0.7224	0.8499
No log	20.0	60	0.9652	0.4156	0.9652	0.9824
No log	21.0	63	0.6498	0.5150	0.6498	0.8061
No log	22.0	66	0.7324	0.5090	0.7324	0.8558
No log	23.0	69	0.6695	0.5697	0.6695	0.8182
No log	24.0	72	0.7989	0.4764	0.7989	0.8938
No log	25.0	75	0.6845	0.5383	0.6845	0.8273
No log	26.0	78	0.7717	0.4960	0.7717	0.8784
No log	27.0	81	0.7915	0.4179	0.7915	0.8896
No log	28.0	84	0.9335	0.4819	0.9335	0.9662
No log	29.0	87	0.8089	0.5257	0.8089	0.8994
No log	30.0	90	1.3363	0.3700	1.3363	1.1560
No log	31.0	93	0.9225	0.4777	0.9225	0.9605
No log	32.0	96	0.7356	0.5675	0.7356	0.8577
No log	33.0	99	1.0873	0.3953	1.0873	1.0427
No log	34.0	102	1.1558	0.3617	1.1558	1.0751
No log	35.0	105	0.7202	0.5536	0.7202	0.8486
No log	36.0	108	0.6805	0.5531	0.6805	0.8249
No log	37.0	111	0.8864	0.4358	0.8864	0.9415
No log	38.0	114	0.7002	0.5617	0.7002	0.8368
No log	39.0	117	0.6441	0.5606	0.6441	0.8026
No log	40.0	120	0.9972	0.4011	0.9972	0.9986
No log	41.0	123	0.7535	0.4166	0.7535	0.8681
No log	42.0	126	0.6324	0.5513	0.6324	0.7952
No log	43.0	129	0.8189	0.3924	0.8189	0.9049
No log	44.0	132	0.8369	0.3995	0.8369	0.9148
No log	45.0	135	0.7035	0.5719	0.7035	0.8388
No log	46.0	138	0.6622	0.5446	0.6622	0.8138
No log	47.0	141	0.9300	0.4000	0.9300	0.9644
No log	48.0	144	0.7179	0.5148	0.7179	0.8473
No log	49.0	147	0.6759	0.5571	0.6759	0.8222
No log	50.0	150	0.6832	0.5300	0.6832	0.8266
No log	51.0	153	0.8732	0.4095	0.8732	0.9344
No log	52.0	156	0.6637	0.5313	0.6637	0.8147
No log	53.0	159	0.7607	0.4691	0.7607	0.8722
No log	54.0	162	0.9066	0.4084	0.9066	0.9522
No log	55.0	165	0.6816	0.5154	0.6816	0.8256
No log	56.0	168	0.6782	0.5341	0.6782	0.8235
No log	57.0	171	0.8924	0.4030	0.8924	0.9447
No log	58.0	174	0.7817	0.4561	0.7817	0.8842
No log	59.0	177	0.6460	0.5239	0.6460	0.8037
No log	60.0	180	0.6717	0.5171	0.6717	0.8196
No log	61.0	183	0.8408	0.4334	0.8408	0.9169
No log	62.0	186	0.6663	0.5034	0.6663	0.8163
No log	63.0	189	0.6753	0.5094	0.6753	0.8217
No log	64.0	192	0.7441	0.4876	0.7441	0.8626
No log	65.0	195	0.6463	0.5216	0.6463	0.8040
No log	66.0	198	0.6749	0.5033	0.6749	0.8215
No log	67.0	201	0.7972	0.4471	0.7972	0.8929
No log	68.0	204	0.7144	0.4939	0.7144	0.8452
No log	69.0	207	0.6627	0.5316	0.6627	0.8141
No log	70.0	210	0.7900	0.4594	0.7900	0.8888
No log	71.0	213	0.7505	0.4876	0.7505	0.8663
No log	72.0	216	0.6681	0.5140	0.6681	0.8174
No log	73.0	219	0.6665	0.5024	0.6665	0.8164
No log	74.0	222	0.7426	0.4558	0.7426	0.8617
No log	75.0	225	0.7159	0.4764	0.7159	0.8461

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k3_k3_fold4

BERT_V8_sp20_lw10_ex40_lo00_k3_k3_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k3_k3_fold4