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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	10.9868	0.0118	10.9848	3.3143
No log	2.0	4	9.2320	0.0	9.2307	3.0382
No log	3.0	6	7.6469	0.0	7.6458	2.7651
No log	4.0	8	4.9997	0.0323	4.9987	2.2358
No log	5.0	10	3.7253	0.0161	3.7247	1.9299
No log	6.0	12	3.5831	0.0041	3.5825	1.8928
No log	7.0	14	2.4132	0.1448	2.4128	1.5533
No log	8.0	16	2.1637	0.1171	2.1627	1.4706
No log	9.0	18	1.6344	0.0553	1.6340	1.2783
No log	10.0	20	1.4526	0.0427	1.4522	1.2051
No log	11.0	22	1.1221	0.0401	1.1218	1.0591
No log	12.0	24	0.9904	0.0445	0.9901	0.9951
No log	13.0	26	0.9672	0.1213	0.9671	0.9834
No log	14.0	28	0.9879	0.1816	0.9880	0.9940
No log	15.0	30	0.9649	0.2792	0.9652	0.9824
No log	16.0	32	0.8473	0.3835	0.8476	0.9207
No log	17.0	34	0.8805	0.3757	0.8810	0.9386
No log	18.0	36	0.8644	0.3849	0.8648	0.9300
No log	19.0	38	0.7758	0.4315	0.7764	0.8811
No log	20.0	40	1.0835	0.4168	1.0844	1.0413
No log	21.0	42	1.1687	0.3840	1.1697	1.0815
No log	22.0	44	0.7475	0.4791	0.7483	0.8650
No log	23.0	46	0.6230	0.5149	0.6236	0.7897
No log	24.0	48	0.6516	0.5218	0.6522	0.8076
No log	25.0	50	0.6572	0.4969	0.6580	0.8112
No log	26.0	52	0.6822	0.5284	0.6831	0.8265
No log	27.0	54	0.6932	0.5216	0.6941	0.8331
No log	28.0	56	0.8453	0.4247	0.8463	0.9199
No log	29.0	58	0.7649	0.4933	0.7658	0.8751
No log	30.0	60	0.9236	0.4591	0.9248	0.9617
No log	31.0	62	1.0915	0.4058	1.0928	1.0454
No log	32.0	64	0.9428	0.4481	0.9439	0.9715
No log	33.0	66	0.7682	0.4699	0.7689	0.8769
No log	34.0	68	0.7226	0.4703	0.7232	0.8504
No log	35.0	70	0.7104	0.4825	0.7110	0.8432
No log	36.0	72	0.7749	0.4605	0.7755	0.8806
No log	37.0	74	0.9828	0.4154	0.9836	0.9918
No log	38.0	76	0.8630	0.4622	0.8637	0.9294
No log	39.0	78	0.7542	0.4651	0.7549	0.8688
No log	40.0	80	0.8528	0.3981	0.8536	0.9239
No log	41.0	82	0.8104	0.4344	0.8111	0.9006

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_AugV8_k1_task1_organization_sp030_lw040_fold3

BERT_AugV8_k1_task1_organization_sp030_lw040_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp030_lw040_fold3