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	16.3573	0.0	16.3575	4.0444
No log	2.0	2	14.4547	0.0	14.4548	3.8019
No log	3.0	3	13.5486	0.0	13.5489	3.6809
No log	4.0	4	13.0881	0.0	13.0884	3.6178
No log	5.0	5	12.5129	0.0	12.5132	3.5374
No log	6.0	6	11.7116	0.0042	11.7119	3.4223
No log	7.0	7	10.5522	0.0048	10.5526	3.2485
No log	8.0	8	8.9649	0.0	8.9654	2.9942
No log	9.0	9	7.7167	0.0	7.7170	2.7780
No log	10.0	10	6.5881	-0.0003	6.5885	2.5668
No log	11.0	11	5.4062	0.0463	5.4066	2.3252
No log	12.0	12	4.7466	0.0141	4.7471	2.1788
No log	13.0	13	4.3813	0.0078	4.3819	2.0933
No log	14.0	14	3.7193	0.0039	3.7199	1.9287
No log	15.0	15	3.0362	0.0039	3.0367	1.7426
No log	16.0	16	2.6581	0.0	2.6586	1.6305
No log	17.0	17	2.4356	0.1155	2.4361	1.5608
No log	18.0	18	2.1202	0.1221	2.1206	1.4562
No log	19.0	19	1.7618	0.0703	1.7623	1.3275
No log	20.0	20	1.5455	0.0487	1.5460	1.2434
No log	21.0	21	1.4255	0.0422	1.4260	1.1941
No log	22.0	22	1.3193	0.0422	1.3199	1.1488
No log	23.0	23	1.1354	0.0318	1.1359	1.0658
No log	24.0	24	1.0258	0.0318	1.0263	1.0131
No log	25.0	25	0.9432	0.0213	0.9437	0.9714
No log	26.0	26	0.8800	0.0213	0.8804	0.9383
No log	27.0	27	0.8065	0.3720	0.8068	0.8982
No log	28.0	28	0.7338	0.4777	0.7342	0.8568
No log	29.0	29	0.7024	0.4504	0.7028	0.8384
No log	30.0	30	0.6687	0.4692	0.6692	0.8180
No log	31.0	31	0.6257	0.4531	0.6260	0.7912
No log	32.0	32	0.5876	0.4203	0.5879	0.7667
No log	33.0	33	0.5386	0.4696	0.5388	0.7340
No log	34.0	34	0.5159	0.4821	0.5160	0.7183
No log	35.0	35	0.5550	0.5245	0.5550	0.7450
No log	36.0	36	0.5457	0.5327	0.5457	0.7387
No log	37.0	37	0.4997	0.5507	0.4997	0.7069
No log	38.0	38	0.4939	0.5583	0.4938	0.7027
No log	39.0	39	0.5095	0.5615	0.5094	0.7137
No log	40.0	40	0.5519	0.5535	0.5519	0.7429
No log	41.0	41	0.5953	0.5644	0.5952	0.7715
No log	42.0	42	0.5634	0.6629	0.5632	0.7505
No log	43.0	43	0.5438	0.6354	0.5436	0.7373
No log	44.0	44	0.5665	0.6154	0.5662	0.7525
No log	45.0	45	0.5836	0.6142	0.5832	0.7637
No log	46.0	46	0.5790	0.6273	0.5788	0.7608
No log	47.0	47	0.5820	0.6281	0.5817	0.7627
No log	48.0	48	0.5896	0.6274	0.5893	0.7677
No log	49.0	49	0.6104	0.6344	0.6101	0.7811
No log	50.0	50	0.6734	0.6125	0.6730	0.8204
No log	51.0	51	0.6928	0.6131	0.6923	0.8321
No log	52.0	52	0.6500	0.6261	0.6497	0.8060
No log	53.0	53	0.5981	0.6595	0.5978	0.7732
No log	54.0	54	0.6034	0.6353	0.6031	0.7766
No log	55.0	55	0.5858	0.6523	0.5855	0.7652
No log	56.0	56	0.6167	0.6350	0.6164	0.7851
No log	57.0	57	0.6561	0.6379	0.6559	0.8099
No log	58.0	58	0.6389	0.6352	0.6387	0.7992
No log	59.0	59	0.5707	0.6760	0.5705	0.7553
No log	60.0	60	0.5664	0.6629	0.5662	0.7525
No log	61.0	61	0.5799	0.6810	0.5797	0.7614
No log	62.0	62	0.5786	0.6692	0.5783	0.7605
No log	63.0	63	0.6074	0.6580	0.6072	0.7792
No log	64.0	64	0.5766	0.6637	0.5763	0.7592
No log	65.0	65	0.5475	0.6533	0.5472	0.7398
No log	66.0	66	0.5438	0.6589	0.5435	0.7372
No log	67.0	67	0.5749	0.6642	0.5746	0.7580
No log	68.0	68	0.6472	0.6673	0.6469	0.8043
No log	69.0	69	0.6564	0.6671	0.6561	0.8100
No log	70.0	70	0.5916	0.6605	0.5913	0.7689
No log	71.0	71	0.5403	0.6503	0.5400	0.7348
No log	72.0	72	0.5437	0.6417	0.5433	0.7371
No log	73.0	73	0.5362	0.6558	0.5358	0.7320
No log	74.0	74	0.5421	0.6661	0.5417	0.7360
No log	75.0	75	0.6087	0.6770	0.6083	0.7799
No log	76.0	76	0.6876	0.6597	0.6872	0.8290
No log	77.0	77	0.6933	0.6608	0.6930	0.8324
No log	78.0	78	0.6394	0.6688	0.6391	0.7994
No log	79.0	79	0.5758	0.6666	0.5754	0.7586
No log	80.0	80	0.5646	0.6622	0.5642	0.7512
No log	81.0	81	0.5734	0.6622	0.5731	0.7570

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

genki10/Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2

Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version3ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2