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	10.6049	-0.0021	10.6029	3.2562
No log	2.0	2	10.3298	0.0	10.3275	3.2136
No log	3.0	3	9.3743	0.0	9.3725	3.0615
No log	4.0	4	8.3272	0.0	8.3257	2.8854
No log	5.0	5	7.4357	0.0	7.4342	2.7266
No log	6.0	6	6.6037	0.0	6.6023	2.5695
No log	7.0	7	5.8968	0.0512	5.8955	2.4281
No log	8.0	8	5.3069	0.0163	5.3057	2.3034
No log	9.0	9	4.8006	0.0076	4.7994	2.1908
No log	10.0	10	4.3201	0.0076	4.3190	2.0782
No log	11.0	11	3.8764	0.0	3.8753	1.9686
No log	12.0	12	3.5750	0.0	3.5740	1.8905
No log	13.0	13	3.1171	0.0	3.1162	1.7653
No log	14.0	14	2.8909	0.0	2.8899	1.7000
No log	15.0	15	2.5860	0.0553	2.5851	1.6078
No log	16.0	16	2.3710	0.1223	2.3702	1.5395
No log	17.0	17	2.2246	0.0756	2.2238	1.4912
No log	18.0	18	1.9884	0.0371	1.9876	1.4098
No log	19.0	19	1.8098	0.0202	1.8091	1.3450
No log	20.0	20	1.6428	0.0202	1.6421	1.2814
No log	21.0	21	1.4701	0.0202	1.4694	1.2122
No log	22.0	22	1.3493	0.0202	1.3486	1.1613
No log	23.0	23	1.2391	0.0202	1.2385	1.1129
No log	24.0	24	1.1443	0.0202	1.1437	1.0695
No log	25.0	25	1.0602	0.0202	1.0596	1.0294
No log	26.0	26	0.9920	0.0202	0.9914	0.9957
No log	27.0	27	0.9406	0.1219	0.9401	0.9696
No log	28.0	28	0.8946	0.3011	0.8940	0.9455
No log	29.0	29	0.8306	0.3366	0.8301	0.9111
No log	30.0	30	0.7907	0.3534	0.7903	0.8890
No log	31.0	31	0.7684	0.3033	0.7680	0.8763
No log	32.0	32	0.7600	0.2437	0.7596	0.8716
No log	33.0	33	0.7479	0.2361	0.7476	0.8646
No log	34.0	34	0.7159	0.2626	0.7157	0.8460
No log	35.0	35	0.6812	0.3119	0.6810	0.8252
No log	36.0	36	0.6851	0.3046	0.6849	0.8276
No log	37.0	37	0.6814	0.3046	0.6812	0.8254
No log	38.0	38	0.6644	0.3191	0.6642	0.8150
No log	39.0	39	0.6080	0.3772	0.6078	0.7796
No log	40.0	40	0.5946	0.3907	0.5944	0.7710
No log	41.0	41	0.6190	0.3719	0.6188	0.7867
No log	42.0	42	0.6090	0.4366	0.6089	0.7803
No log	43.0	43	0.6002	0.4777	0.6000	0.7746
No log	44.0	44	0.5445	0.5216	0.5443	0.7378
No log	45.0	45	0.5426	0.5301	0.5423	0.7364
No log	46.0	46	0.5450	0.5947	0.5447	0.7381
No log	47.0	47	0.5954	0.5897	0.5951	0.7714
No log	48.0	48	0.6428	0.5810	0.6425	0.8016
No log	49.0	49	0.6033	0.6112	0.6029	0.7765
No log	50.0	50	0.5853	0.5988	0.5849	0.7648
No log	51.0	51	0.6195	0.5566	0.6191	0.7868
No log	52.0	52	0.5962	0.5924	0.5958	0.7719
No log	53.0	53	0.6095	0.6188	0.6091	0.7804
No log	54.0	54	0.6593	0.6206	0.6588	0.8117
No log	55.0	55	0.6490	0.6267	0.6486	0.8053
No log	56.0	56	0.6144	0.6326	0.6139	0.7835
No log	57.0	57	0.6010	0.6295	0.6005	0.7749
No log	58.0	58	0.6108	0.6289	0.6103	0.7812
No log	59.0	59	0.6263	0.6229	0.6259	0.7911
No log	60.0	60	0.6482	0.6135	0.6478	0.8048
No log	61.0	61	0.6523	0.6124	0.6518	0.8073
No log	62.0	62	0.6233	0.6219	0.6229	0.7892
No log	63.0	63	0.6408	0.6191	0.6403	0.8002
No log	64.0	64	0.6710	0.6214	0.6705	0.8188
No log	65.0	65	0.6465	0.6237	0.6460	0.8037
No log	66.0	66	0.6253	0.5988	0.6248	0.7905
No log	67.0	67	0.6252	0.5878	0.6247	0.7904
No log	68.0	68	0.6227	0.6256	0.6222	0.7888
No log	69.0	69	0.6338	0.6231	0.6333	0.7958
No log	70.0	70	0.6004	0.6390	0.5999	0.7745
No log	71.0	71	0.5831	0.6368	0.5827	0.7633
No log	72.0	72	0.5865	0.6407	0.5860	0.7655
No log	73.0	73	0.5934	0.6301	0.5930	0.7701
No log	74.0	74	0.6436	0.6231	0.6431	0.8019
No log	75.0	75	0.6363	0.6240	0.6358	0.7974
No log	76.0	76	0.5843	0.6222	0.5839	0.7642
No log	77.0	77	0.5709	0.6426	0.5706	0.7554
No log	78.0	78	0.5766	0.6227	0.5762	0.7591
No log	79.0	79	0.6054	0.6174	0.6050	0.7778
No log	80.0	80	0.6457	0.6266	0.6453	0.8033
No log	81.0	81	0.6393	0.6255	0.6388	0.7993
No log	82.0	82	0.5942	0.6225	0.5937	0.7705
No log	83.0	83	0.5715	0.6197	0.5711	0.7557
No log	84.0	84	0.5718	0.6189	0.5715	0.7559
No log	85.0	85	0.5890	0.6208	0.5886	0.7672
No log	86.0	86	0.6232	0.6253	0.6227	0.7891
No log	87.0	87	0.6317	0.6235	0.6312	0.7945
No log	88.0	88	0.6103	0.6256	0.6098	0.7809
No log	89.0	89	0.5980	0.6290	0.5976	0.7730
No log	90.0	90	0.6039	0.6263	0.6035	0.7768
No log	91.0	91	0.5921	0.6290	0.5917	0.7692
No log	92.0	92	0.5908	0.6290	0.5903	0.7683
No log	93.0	93	0.5943	0.6290	0.5938	0.7706
No log	94.0	94	0.5963	0.6290	0.5959	0.7720
No log	95.0	95	0.6071	0.6298	0.6067	0.7789
No log	96.0	96	0.6164	0.6254	0.6160	0.7848
No log	97.0	97	0.6308	0.6250	0.6303	0.7939

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold3

Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version12AGAINNNASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold3