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	9.7985	0.0018	9.7985	3.1303
No log	2.0	4	9.1278	0.0018	9.1278	3.0212
No log	3.0	6	8.0154	0.0	8.0154	2.8311
No log	4.0	8	6.6835	0.0	6.6835	2.5853
No log	5.0	10	5.4121	0.0396	5.4121	2.3264
No log	6.0	12	4.2099	0.0079	4.2099	2.0518
No log	7.0	14	3.5033	0.0040	3.5033	1.8717
No log	8.0	16	2.8007	0.0040	2.8007	1.6735
No log	9.0	18	2.1977	0.1636	2.1977	1.4825
No log	10.0	20	1.6914	0.0610	1.6914	1.3005
No log	11.0	22	1.4067	0.0634	1.4067	1.1860
No log	12.0	24	1.2390	0.0734	1.2390	1.1131
No log	13.0	26	0.9958	0.0734	0.9958	0.9979
No log	14.0	28	0.9855	0.0818	0.9855	0.9927
No log	15.0	30	1.2960	0.1654	1.2960	1.1384
No log	16.0	32	1.3574	0.1963	1.3574	1.1651
No log	17.0	34	0.9311	0.3733	0.9311	0.9649
No log	18.0	36	0.7801	0.4265	0.7801	0.8832
No log	19.0	38	0.9015	0.3805	0.9015	0.9495
No log	20.0	40	1.1423	0.3310	1.1423	1.0688
No log	21.0	42	0.8770	0.4097	0.8770	0.9365
No log	22.0	44	0.7283	0.4369	0.7283	0.8534
No log	23.0	46	0.8021	0.4144	0.8021	0.8956
No log	24.0	48	0.9987	0.3610	0.9987	0.9994
No log	25.0	50	0.8996	0.3815	0.8996	0.9485
No log	26.0	52	0.7810	0.5058	0.7810	0.8837
No log	27.0	54	0.7767	0.4696	0.7767	0.8813
No log	28.0	56	1.0126	0.4339	1.0126	1.0063
No log	29.0	58	1.1389	0.3825	1.1389	1.0672
No log	30.0	60	1.0540	0.4175	1.0540	1.0266
No log	31.0	62	1.0030	0.4430	1.0030	1.0015
No log	32.0	64	0.9775	0.4849	0.9775	0.9887
No log	33.0	66	0.9731	0.4639	0.9731	0.9864
No log	34.0	68	1.0398	0.4110	1.0398	1.0197
No log	35.0	70	1.0281	0.4259	1.0281	1.0139
No log	36.0	72	1.1516	0.4585	1.1516	1.0731
No log	37.0	74	0.9552	0.4771	0.9552	0.9773
No log	38.0	76	1.0382	0.4214	1.0382	1.0189
No log	39.0	78	0.9062	0.4927	0.9062	0.9519
No log	40.0	80	0.8470	0.5074	0.8470	0.9203
No log	41.0	82	0.9115	0.4673	0.9115	0.9547
No log	42.0	84	0.9485	0.4242	0.9485	0.9739
No log	43.0	86	0.9162	0.4741	0.9162	0.9572
No log	44.0	88	0.8784	0.4369	0.8784	0.9372
No log	45.0	90	0.8353	0.4682	0.8353	0.9140
No log	46.0	92	0.8248	0.4880	0.8248	0.9082
No log	47.0	94	0.8775	0.4931	0.8775	0.9367
No log	48.0	96	0.8572	0.4726	0.8572	0.9258
No log	49.0	98	0.8937	0.4450	0.8937	0.9454
No log	50.0	100	0.9214	0.4442	0.9214	0.9599
No log	51.0	102	0.8870	0.4439	0.8870	0.9418
No log	52.0	104	0.8722	0.4426	0.8722	0.9339
No log	53.0	106	0.7764	0.5350	0.7764	0.8811
No log	54.0	108	0.7690	0.5371	0.7690	0.8770
No log	55.0	110	0.8420	0.4905	0.8420	0.9176
No log	56.0	112	0.8479	0.4752	0.8479	0.9208
No log	57.0	114	0.8615	0.4746	0.8615	0.9282
No log	58.0	116	0.8719	0.4605	0.8719	0.9337
No log	59.0	118	0.8644	0.4443	0.8644	0.9297
No log	60.0	120	0.8483	0.4496	0.8483	0.9211
No log	61.0	122	0.8124	0.4580	0.8124	0.9013
No log	62.0	124	0.8028	0.4583	0.8028	0.8960
No log	63.0	126	0.8197	0.4656	0.8197	0.9054
No log	64.0	128	0.8764	0.4569	0.8764	0.9362
No log	65.0	130	0.9125	0.4365	0.9125	0.9553
No log	66.0	132	0.9413	0.3642	0.9413	0.9702
No log	67.0	134	0.8699	0.4213	0.8699	0.9327
No log	68.0	136	0.8073	0.4753	0.8073	0.8985
No log	69.0	138	0.7996	0.4482	0.7996	0.8942

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_sp060_lw040_fold4

BERT_AugV8_k1_task1_organization_sp060_lw040_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_AugV8_k1_task1_organization_sp060_lw040_fold4