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	12.4769	-0.0013	12.4749	3.5320
No log	2.0	2	11.0043	0.0100	11.0024	3.3170
No log	3.0	3	10.1810	0.0	10.1790	3.1905
No log	4.0	4	9.2365	0.0	9.2347	3.0389
No log	5.0	5	8.2534	0.0	8.2517	2.8726
No log	6.0	6	7.5170	0.0	7.5153	2.7414
No log	7.0	7	6.8504	0.0	6.8488	2.6170
No log	8.0	8	6.2095	-0.0036	6.2080	2.4916
No log	9.0	9	5.6026	0.0167	5.6012	2.3667
No log	10.0	10	5.0398	0.0076	5.0384	2.2446
No log	11.0	11	4.5277	0.0	4.5265	2.1276
No log	12.0	12	4.0249	0.0	4.0237	2.0059
No log	13.0	13	3.6448	0.0	3.6436	1.9088
No log	14.0	14	3.1751	0.0	3.1740	1.7816
No log	15.0	15	2.8105	0.0	2.8097	1.6762
No log	16.0	16	2.4579	0.1433	2.4570	1.5675
No log	17.0	17	2.1794	0.1109	2.1785	1.4760
No log	18.0	18	1.9305	0.0623	1.9297	1.3891
No log	19.0	19	1.8210	0.0788	1.8203	1.3492
No log	20.0	20	1.5572	0.0488	1.5565	1.2476
No log	21.0	21	1.4831	0.0401	1.4824	1.2175
No log	22.0	22	1.3163	0.0302	1.3156	1.1470
No log	23.0	23	1.1872	0.0302	1.1867	1.0893
No log	24.0	24	1.2170	0.0302	1.2165	1.1030
No log	25.0	25	1.1020	0.0302	1.1016	1.0496
No log	26.0	26	0.9422	0.0445	0.9418	0.9704
No log	27.0	27	0.8852	0.2607	0.8848	0.9406
No log	28.0	28	0.8682	0.3075	0.8679	0.9316
No log	29.0	29	0.8384	0.3231	0.8382	0.9155
No log	30.0	30	0.8386	0.3108	0.8384	0.9156
No log	31.0	31	0.7718	0.3900	0.7717	0.8784
No log	32.0	32	0.7240	0.4442	0.7239	0.8509
No log	33.0	33	0.6754	0.5036	0.6754	0.8218
No log	34.0	34	0.6689	0.5106	0.6689	0.8179
No log	35.0	35	0.8270	0.4500	0.8271	0.9094
No log	36.0	36	0.8414	0.4435	0.8416	0.9174
No log	37.0	37	0.7194	0.5209	0.7196	0.8483
No log	38.0	38	0.7345	0.5155	0.7347	0.8572
No log	39.0	39	0.9151	0.4470	0.9154	0.9568
No log	40.0	40	0.9501	0.4463	0.9505	0.9749
No log	41.0	41	0.7920	0.5090	0.7924	0.8902
No log	42.0	42	0.7382	0.5074	0.7386	0.8594
No log	43.0	43	0.7625	0.4964	0.7630	0.8735
No log	44.0	44	0.8202	0.4721	0.8207	0.9059
No log	45.0	45	0.7794	0.4727	0.7799	0.8831
No log	46.0	46	0.8289	0.4711	0.8294	0.9107
No log	47.0	47	0.8059	0.4971	0.8065	0.8980
No log	48.0	48	0.7243	0.5471	0.7248	0.8514
No log	49.0	49	0.7445	0.5235	0.7450	0.8631
No log	50.0	50	0.7849	0.4926	0.7855	0.8863
No log	51.0	51	0.8633	0.4838	0.8638	0.9294
No log	52.0	52	0.8266	0.4841	0.8271	0.9095
No log	53.0	53	0.7708	0.5147	0.7713	0.8782
No log	54.0	54	0.8160	0.4926	0.8165	0.9036
No log	55.0	55	0.8050	0.4855	0.8055	0.8975
No log	56.0	56	0.7702	0.5131	0.7706	0.8779
No log	57.0	57	0.7847	0.5106	0.7852	0.8861
No log	58.0	58	0.8913	0.4701	0.8918	0.9444
No log	59.0	59	0.8905	0.4675	0.8910	0.9439
No log	60.0	60	0.7950	0.5139	0.7954	0.8919
No log	61.0	61	0.7746	0.5225	0.7751	0.8804
No log	62.0	62	0.7444	0.5505	0.7448	0.8630
No log	63.0	63	0.7724	0.5274	0.7729	0.8791
No log	64.0	64	0.8572	0.4865	0.8577	0.9261
No log	65.0	65	0.8644	0.4814	0.8649	0.9300
No log	66.0	66	0.7982	0.5160	0.7987	0.8937
No log	67.0	67	0.7659	0.5406	0.7663	0.8754
No log	68.0	68	0.7682	0.5409	0.7687	0.8767
No log	69.0	69	0.8092	0.5146	0.8096	0.8998
No log	70.0	70	0.8029	0.5257	0.8034	0.8963
No log	71.0	71	0.7640	0.5393	0.7644	0.8743
No log	72.0	72	0.7621	0.5488	0.7625	0.8732
No log	73.0	73	0.7856	0.5400	0.7862	0.8867
No log	74.0	74	0.8544	0.5050	0.8550	0.9246
No log	75.0	75	0.8788	0.4974	0.8794	0.9378
No log	76.0	76	0.8544	0.5063	0.8550	0.9247
No log	77.0	77	0.8033	0.5371	0.8039	0.8966
No log	78.0	78	0.7678	0.5403	0.7683	0.8765
No log	79.0	79	0.7657	0.5365	0.7662	0.8753
No log	80.0	80	0.7656	0.5370	0.7660	0.8752
No log	81.0	81	0.7683	0.5402	0.7688	0.8768
No log	82.0	82	0.7895	0.5397	0.7901	0.8889

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/ASAP_nosemantic_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold3

ASAP_nosemantic_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
ASAP_nosemantic_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold3