Version_weird_ASAP_FineTuningBERT_AugV12_k4_task1_organization_k4_k4_fold3

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2919
• Qwk: 0.5117
• Mse: 1.2915
• Rmse: 1.1365

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• 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	2	11.1127	0.0096	11.1108	3.3333
No log	2.0	4	9.7402	0.0	9.7383	3.1206
No log	3.0	6	8.6794	0.0	8.6776	2.9458
No log	4.0	8	7.6563	0.0	7.6546	2.7667
No log	5.0	10	6.2389	0.0113	6.2375	2.4975
No log	6.0	12	4.8836	0.0110	4.8824	2.2096
No log	7.0	14	4.4741	0.0	4.4728	2.1149
No log	8.0	16	2.7779	0.0067	2.7770	1.6664
No log	9.0	18	2.5292	-0.0208	2.5283	1.5901
No log	10.0	20	2.2690	0.1246	2.2681	1.5060
No log	11.0	22	2.2322	0.1028	2.2314	1.4938
No log	12.0	24	1.4297	0.0102	1.4291	1.1955
No log	13.0	26	1.0374	0.0202	1.0369	1.0183
No log	14.0	28	0.9199	0.3044	0.9194	0.9589
No log	15.0	30	0.8441	0.1125	0.8436	0.9185
No log	16.0	32	0.8408	0.0553	0.8405	0.9168
No log	17.0	34	0.8872	0.0468	0.8869	0.9417
No log	18.0	36	1.1041	0.0454	1.1039	1.0507
No log	19.0	38	1.2496	0.1184	1.2494	1.1178
No log	20.0	40	1.3955	0.1701	1.3953	1.1812
No log	21.0	42	1.4742	0.1279	1.4741	1.2141
No log	22.0	44	1.8307	0.1136	1.8306	1.3530
No log	23.0	46	1.8743	0.1540	1.8744	1.3691
No log	24.0	48	1.3418	0.2499	1.3421	1.1585
No log	25.0	50	1.4000	0.3122	1.4002	1.1833
No log	26.0	52	0.7883	0.4514	0.7886	0.8880
No log	27.0	54	0.8842	0.4562	0.8845	0.9405
No log	28.0	56	0.8091	0.4782	0.8095	0.8997
No log	29.0	58	0.8671	0.5193	0.8674	0.9314
No log	30.0	60	1.1537	0.4649	1.1538	1.0741
No log	31.0	62	0.8885	0.5334	0.8885	0.9426
No log	32.0	64	0.6855	0.5952	0.6856	0.8280
No log	33.0	66	0.8459	0.5718	0.8458	0.9197
No log	34.0	68	1.3321	0.4741	1.3317	1.1540
No log	35.0	70	1.0430	0.5254	1.0428	1.0212
No log	36.0	72	0.8966	0.5762	0.8966	0.9469
No log	37.0	74	0.9836	0.5639	0.9835	0.9917
No log	38.0	76	1.2988	0.5030	1.2984	1.1395
No log	39.0	78	1.3520	0.4863	1.3516	1.1626
No log	40.0	80	0.9535	0.5621	0.9534	0.9764
No log	41.0	82	0.9675	0.5621	0.9673	0.9835
No log	42.0	84	1.1669	0.5255	1.1667	1.0801
No log	43.0	86	1.0110	0.5385	1.0108	1.0054
No log	44.0	88	1.1482	0.5155	1.1481	1.0715
No log	45.0	90	1.3793	0.4934	1.3790	1.1743
No log	46.0	92	1.3271	0.4976	1.3267	1.1518
No log	47.0	94	1.0184	0.5481	1.0183	1.0091
No log	48.0	96	0.9180	0.5581	0.9179	0.9581
No log	49.0	98	1.0982	0.5360	1.0980	1.0478
No log	50.0	100	1.1822	0.5233	1.1819	1.0871
No log	51.0	102	1.1085	0.5364	1.1082	1.0527
No log	52.0	104	1.2919	0.5117	1.2915	1.1365

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0