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	15.7511	0.0	15.7511	3.9688
No log	2.0	2	13.5676	0.0	13.5676	3.6834
No log	3.0	3	12.3752	-0.0029	12.3752	3.5178
No log	4.0	4	11.5602	-0.0083	11.5602	3.4000
No log	5.0	5	11.2364	0.0	11.2364	3.3521
No log	6.0	6	10.6642	0.0	10.6642	3.2656
No log	7.0	7	9.8756	0.0	9.8756	3.1425
No log	8.0	8	8.9433	0.0	8.9433	2.9905
No log	9.0	9	8.0918	0.0	8.0918	2.8446
No log	10.0	10	7.3746	0.0	7.3746	2.7156
No log	11.0	11	6.9017	0.0	6.9017	2.6271
No log	12.0	12	6.6364	0.0066	6.6364	2.5761
No log	13.0	13	6.2989	0.0138	6.2989	2.5098
No log	14.0	14	5.4311	0.0	5.4311	2.3305
No log	15.0	15	4.7472	0.0	4.7472	2.1788
No log	16.0	16	4.4870	0.0	4.4870	2.1183
No log	17.0	17	3.8466	0.0	3.8466	1.9613
No log	18.0	18	3.2928	0.0	3.2928	1.8146
No log	19.0	19	2.9444	0.0133	2.9444	1.7159
No log	20.0	20	2.8603	0.0495	2.8603	1.6912
No log	21.0	21	2.5749	0.12	2.5749	1.6046
No log	22.0	22	2.3225	0.0323	2.3225	1.5240
No log	23.0	23	2.1249	0.0712	2.1249	1.4577
No log	24.0	24	2.1336	0.0246	2.1336	1.4607
No log	25.0	25	2.0245	0.0246	2.0245	1.4229
No log	26.0	26	1.7431	0.0	1.7431	1.3203
No log	27.0	27	1.5851	0.0	1.5851	1.2590
No log	28.0	28	1.4765	0.0	1.4765	1.2151
No log	29.0	29	1.3599	0.0	1.3599	1.1662
No log	30.0	30	1.2995	0.0	1.2995	1.1399
No log	31.0	31	1.2281	0.0787	1.2281	1.1082
No log	32.0	32	1.1157	0.3162	1.1157	1.0563
No log	33.0	33	1.0636	0.3756	1.0636	1.0313
No log	34.0	34	1.0339	0.3929	1.0339	1.0168
No log	35.0	35	0.9793	0.3456	0.9793	0.9896
No log	36.0	36	0.9574	0.3211	0.9574	0.9785
No log	37.0	37	0.9155	0.3394	0.9155	0.9568
No log	38.0	38	0.8728	0.3756	0.8728	0.9342
No log	39.0	39	0.8391	0.4054	0.8391	0.9160
No log	40.0	40	0.8294	0.3455	0.8294	0.9107
No log	41.0	41	0.8069	0.3694	0.8069	0.8983
No log	42.0	42	0.7748	0.3991	0.7748	0.8802
No log	43.0	43	0.7627	0.3991	0.7627	0.8733
No log	44.0	44	0.7808	0.3756	0.7808	0.8836
No log	45.0	45	0.7559	0.3867	0.7559	0.8694
No log	46.0	46	0.6636	0.5361	0.6636	0.8146
No log	47.0	47	0.6328	0.5793	0.6328	0.7955
No log	48.0	48	0.6395	0.6027	0.6395	0.7997
No log	49.0	49	0.7188	0.6331	0.7188	0.8479
No log	50.0	50	0.8714	0.5637	0.8714	0.9335
No log	51.0	51	0.8844	0.5637	0.8844	0.9404
No log	52.0	52	0.8225	0.6134	0.8225	0.9069
No log	53.0	53	0.6969	0.6267	0.6969	0.8348
No log	54.0	54	0.6614	0.6322	0.6614	0.8133
No log	55.0	55	0.6627	0.6686	0.6627	0.8141
No log	56.0	56	0.7274	0.6419	0.7274	0.8529
No log	57.0	57	0.8936	0.6000	0.8936	0.9453
No log	58.0	58	1.0468	0.5433	1.0468	1.0231
No log	59.0	59	1.1266	0.4910	1.1266	1.0614
No log	60.0	60	1.0424	0.5508	1.0424	1.0210
No log	61.0	61	0.8598	0.6022	0.8598	0.9273
No log	62.0	62	0.8087	0.6129	0.8087	0.8993
No log	63.0	63	0.8770	0.6066	0.8770	0.9365
No log	64.0	64	1.0715	0.5501	1.0715	1.0351
No log	65.0	65	1.2393	0.4803	1.2393	1.1132
No log	66.0	66	1.2298	0.5385	1.2298	1.1090
No log	67.0	67	1.1139	0.5418	1.1139	1.0554
No log	68.0	68	0.9666	0.6088	0.9666	0.9831
No log	69.0	69	0.9243	0.6088	0.9243	0.9614
No log	70.0	70	0.9310	0.6088	0.9310	0.9649
No log	71.0	71	1.0278	0.5778	1.0278	1.0138
No log	72.0	72	1.0462	0.5647	1.0462	1.0228
No log	73.0	73	1.1372	0.5455	1.1372	1.0664
No log	74.0	74	1.1435	0.5540	1.1435	1.0694
No log	75.0	75	1.0354	0.5845	1.0354	1.0175

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version12LowDevASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2

Version12LowDevASAP_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/
Version12LowDevASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold2