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: 150

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	8	5.1014	0.0	5.1000	2.2583
No log	2.0	16	1.9233	0.0463	1.9226	1.3866
No log	3.0	24	1.0140	0.0102	1.0136	1.0068
No log	4.0	32	2.0187	0.1629	2.0181	1.4206
No log	5.0	40	1.2859	0.2885	1.2857	1.1339
No log	6.0	48	0.7858	0.3959	0.7858	0.8865
No log	7.0	56	0.9671	0.3913	0.9677	0.9837
No log	8.0	64	1.6000	0.3233	1.6009	1.2653
No log	9.0	72	0.7580	0.4915	0.7587	0.8710
No log	10.0	80	1.2826	0.3578	1.2841	1.1332
No log	11.0	88	1.0307	0.4101	1.0319	1.0158
No log	12.0	96	0.8102	0.4693	0.8110	0.9006
No log	13.0	104	1.2018	0.3723	1.2029	1.0968
No log	14.0	112	1.4425	0.3183	1.4440	1.2017
No log	15.0	120	1.0791	0.3766	1.0805	1.0395
No log	16.0	128	1.0587	0.3693	1.0602	1.0297
No log	17.0	136	1.9183	0.2632	1.9197	1.3855
No log	18.0	144	1.1195	0.3689	1.1205	1.0585
No log	19.0	152	0.9935	0.3864	0.9944	0.9972
No log	20.0	160	0.9411	0.3944	0.9421	0.9706
No log	21.0	168	1.1894	0.3789	1.1904	1.0911
No log	22.0	176	1.0018	0.4356	1.0030	1.0015
No log	23.0	184	0.8975	0.4407	0.8986	0.9479
No log	24.0	192	1.4943	0.3054	1.4954	1.2228
No log	25.0	200	1.1360	0.4095	1.1372	1.0664
No log	26.0	208	0.9222	0.4828	0.9233	0.9609
No log	27.0	216	1.2027	0.3859	1.2036	1.0971
No log	28.0	224	1.0863	0.4369	1.0873	1.0427
No log	29.0	232	1.1734	0.4041	1.1744	1.0837
No log	30.0	240	0.9515	0.4663	0.9524	0.9759
No log	31.0	248	0.8873	0.4780	0.8882	0.9425
No log	32.0	256	1.3513	0.3593	1.3521	1.1628
No log	33.0	264	0.9137	0.5002	0.9146	0.9563
No log	34.0	272	1.0409	0.4908	1.0418	1.0207
No log	35.0	280	0.9449	0.4903	0.9458	0.9725
No log	36.0	288	1.0071	0.4513	1.0079	1.0040
No log	37.0	296	0.8881	0.4724	0.8889	0.9428
No log	38.0	304	0.8880	0.4722	0.8888	0.9428
No log	39.0	312	1.0165	0.4880	1.0175	1.0087
No log	40.0	320	0.9559	0.4890	0.9569	0.9782
No log	41.0	328	0.9370	0.4512	0.9379	0.9685
No log	42.0	336	0.9699	0.4633	0.9706	0.9852
No log	43.0	344	1.1237	0.4107	1.1249	1.0606
No log	44.0	352	0.9905	0.5049	0.9913	0.9957
No log	45.0	360	0.8388	0.5205	0.8395	0.9162
No log	46.0	368	0.9340	0.4830	0.9348	0.9668
No log	47.0	376	1.0620	0.4171	1.0628	1.0309
No log	48.0	384	0.9455	0.5070	0.9463	0.9728
No log	49.0	392	0.9517	0.4588	0.9526	0.9760
No log	50.0	400	1.0468	0.4235	1.0478	1.0236
No log	51.0	408	0.9598	0.4847	0.9607	0.9802
No log	52.0	416	1.0484	0.4310	1.0493	1.0244
No log	53.0	424	0.9479	0.4984	0.9488	0.9741
No log	54.0	432	1.0209	0.4427	1.0218	1.0109
No log	55.0	440	1.0099	0.4270	1.0107	1.0054
No log	56.0	448	0.9876	0.4375	0.9885	0.9942
No log	57.0	456	1.0512	0.4251	1.0523	1.0258
No log	58.0	464	0.8674	0.4771	0.8682	0.9318
No log	59.0	472	0.8483	0.5190	0.8490	0.9214
No log	60.0	480	0.8646	0.4867	0.8652	0.9302
No log	61.0	488	0.8763	0.4621	0.8771	0.9365
No log	62.0	496	0.9047	0.4733	0.9054	0.9515
0.309	63.0	504	0.8251	0.5070	0.8258	0.9087
0.309	64.0	512	0.9551	0.4976	0.9560	0.9778
0.309	65.0	520	0.9718	0.4639	0.9728	0.9863
0.309	66.0	528	0.8893	0.5076	0.8900	0.9434
0.309	67.0	536	0.8416	0.5087	0.8424	0.9178
0.309	68.0	544	0.8531	0.4998	0.8539	0.9241
0.309	69.0	552	0.9538	0.4980	0.9547	0.9771
0.309	70.0	560	0.8806	0.5111	0.8814	0.9388
0.309	71.0	568	0.8894	0.5086	0.8902	0.9435
0.309	72.0	576	0.9683	0.4553	0.9692	0.9845
0.309	73.0	584	0.9192	0.4868	0.9200	0.9592
0.309	74.0	592	0.9122	0.4573	0.9130	0.9555
0.309	75.0	600	0.9852	0.4700	0.9858	0.9929

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/Version24NewTestASAP_FineTuningBERT_AugV24_k15_task1_organization_k15_k15_fold3

Version24NewTestASAP_FineTuningBERT_AugV24_k15_task1_organization_k15_k15_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
Version24NewTestASAP_FineTuningBERT_AugV24_k15_task1_organization_k15_k15_fold3