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	1	12.3128	-0.0050	12.3128	3.5090
No log	2.0	2	11.3133	-0.0238	11.3133	3.3635
No log	3.0	3	10.1525	-0.0001	10.1525	3.1863
No log	4.0	4	9.1311	0.0018	9.1311	3.0218
No log	5.0	5	8.2865	0.0018	8.2865	2.8786
No log	6.0	6	7.4430	0.0018	7.4430	2.7282
No log	7.0	7	6.6346	0.0018	6.6346	2.5758
No log	8.0	8	6.0942	0.0000	6.0942	2.4686
No log	9.0	9	5.5193	0.0091	5.5193	2.3493
No log	10.0	10	4.8050	0.0118	4.8050	2.1920
No log	11.0	11	4.2779	0.0118	4.2779	2.0683
No log	12.0	12	3.8501	0.0040	3.8501	1.9622
No log	13.0	13	3.4038	0.0040	3.4038	1.8449
No log	14.0	14	3.0356	0.0040	3.0356	1.7423
No log	15.0	15	2.7580	0.0040	2.7580	1.6607
No log	16.0	16	2.4072	0.0669	2.4072	1.5515
No log	17.0	17	2.1295	0.1369	2.1295	1.4593
No log	18.0	18	1.9270	0.0634	1.9270	1.3881
No log	19.0	19	1.7377	0.0445	1.7377	1.3182
No log	20.0	20	1.5628	0.0420	1.5628	1.2501
No log	21.0	21	1.4162	0.0420	1.4162	1.1901
No log	22.0	22	1.2915	0.0316	1.2915	1.1365
No log	23.0	23	1.1815	0.0316	1.1815	1.0869
No log	24.0	24	1.0802	0.0316	1.0802	1.0393
No log	25.0	25	0.9951	0.0316	0.9951	0.9976
No log	26.0	26	0.9290	0.0316	0.9290	0.9639
No log	27.0	27	0.8644	0.0864	0.8644	0.9297
No log	28.0	28	0.8042	0.3508	0.8042	0.8968
No log	29.0	29	0.7463	0.4541	0.7463	0.8639
No log	30.0	30	0.6966	0.5134	0.6966	0.8346
No log	31.0	31	0.6554	0.5249	0.6554	0.8096
No log	32.0	32	0.6277	0.5433	0.6277	0.7923
No log	33.0	33	0.5880	0.5078	0.5880	0.7668
No log	34.0	34	0.5853	0.4943	0.5853	0.7650
No log	35.0	35	0.5458	0.5129	0.5458	0.7388
No log	36.0	36	0.5409	0.5784	0.5409	0.7354
No log	37.0	37	0.5230	0.5813	0.5230	0.7232
No log	38.0	38	0.5194	0.5245	0.5194	0.7207
No log	39.0	39	0.5428	0.4999	0.5428	0.7367
No log	40.0	40	0.5486	0.5048	0.5486	0.7407
No log	41.0	41	0.5032	0.5269	0.5032	0.7094
No log	42.0	42	0.5068	0.5443	0.5068	0.7119
No log	43.0	43	0.5460	0.5682	0.5460	0.7389
No log	44.0	44	0.6338	0.5420	0.6338	0.7961
No log	45.0	45	0.6498	0.5522	0.6498	0.8061
No log	46.0	46	0.5623	0.6123	0.5623	0.7499
No log	47.0	47	0.5545	0.6145	0.5545	0.7446
No log	48.0	48	0.6284	0.5922	0.6284	0.7927
No log	49.0	49	0.7173	0.5538	0.7173	0.8469
No log	50.0	50	0.7453	0.5550	0.7453	0.8633
No log	51.0	51	0.6606	0.5838	0.6606	0.8128
No log	52.0	52	0.6265	0.6108	0.6265	0.7915
No log	53.0	53	0.7093	0.5769	0.7093	0.8422
No log	54.0	54	0.8507	0.5370	0.8507	0.9224
No log	55.0	55	0.8678	0.5333	0.8678	0.9316
No log	56.0	56	0.7310	0.5731	0.7310	0.8550
No log	57.0	57	0.7067	0.5885	0.7067	0.8406
No log	58.0	58	0.7456	0.5866	0.7456	0.8635
No log	59.0	59	0.8969	0.5495	0.8969	0.9471
No log	60.0	60	0.9514	0.5411	0.9514	0.9754
No log	61.0	61	0.8534	0.5763	0.8534	0.9238
No log	62.0	62	0.8427	0.5819	0.8427	0.9180
No log	63.0	63	0.9688	0.5438	0.9688	0.9843
No log	64.0	64	1.1581	0.4938	1.1581	1.0762
No log	65.0	65	1.1362	0.5074	1.1362	1.0659
No log	66.0	66	0.9471	0.5524	0.9471	0.9732
No log	67.0	67	0.9145	0.5627	0.9145	0.9563

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version5ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold4

Version5ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version5ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold4