ASAP_FineTuningBERT_AugV6_k3_task1_organization_k3_k3_fold0

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: 0.9276
• Qwk: 0.4192
• Mse: 0.9276
• Rmse: 0.9631

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	3	12.1180	0.0098	12.1180	3.4811
No log	2.0	6	7.8344	0.0	7.8344	2.7990
No log	3.0	9	4.9662	0.0241	4.9662	2.2285
No log	4.0	12	3.0220	0.0077	3.0220	1.7384
No log	5.0	15	1.8533	0.0748	1.8533	1.3614
No log	6.0	18	1.3394	0.0612	1.3394	1.1573
No log	7.0	21	1.0964	0.0316	1.0964	1.0471
No log	8.0	24	1.3255	0.0583	1.3255	1.1513
No log	9.0	27	0.8987	0.1892	0.8987	0.9480
No log	10.0	30	0.9200	0.2404	0.9200	0.9592
No log	11.0	33	0.9291	0.3359	0.9291	0.9639
No log	12.0	36	0.7327	0.4496	0.7327	0.8560
No log	13.0	39	0.6272	0.4167	0.6272	0.7920
No log	14.0	42	0.6574	0.4074	0.6574	0.8108
No log	15.0	45	0.5988	0.4090	0.5988	0.7738
No log	16.0	48	0.6758	0.4061	0.6758	0.8220
No log	17.0	51	0.6867	0.4232	0.6867	0.8287
No log	18.0	54	0.8726	0.3507	0.8726	0.9341
No log	19.0	57	0.8223	0.3507	0.8223	0.9068
No log	20.0	60	1.0142	0.3820	1.0142	1.0071
No log	21.0	63	0.7111	0.4906	0.7111	0.8433
No log	22.0	66	0.7631	0.4780	0.7631	0.8736
No log	23.0	69	0.7897	0.4561	0.7897	0.8886
No log	24.0	72	0.8612	0.4382	0.8612	0.9280
No log	25.0	75	0.9182	0.4264	0.9182	0.9582
No log	26.0	78	0.8725	0.4650	0.8725	0.9341
No log	27.0	81	0.8638	0.4366	0.8638	0.9294
No log	28.0	84	0.9675	0.4160	0.9675	0.9836
No log	29.0	87	0.8886	0.4346	0.8886	0.9427
No log	30.0	90	1.0147	0.4137	1.0147	1.0073
No log	31.0	93	0.9390	0.4338	0.9390	0.9690
No log	32.0	96	0.9068	0.4269	0.9068	0.9523
No log	33.0	99	0.9030	0.4547	0.9030	0.9503
No log	34.0	102	0.8759	0.4700	0.8759	0.9359
No log	35.0	105	0.9140	0.4522	0.9140	0.9560
No log	36.0	108	0.9439	0.4284	0.9439	0.9716
No log	37.0	111	0.9039	0.4366	0.9039	0.9507
No log	38.0	114	0.8794	0.4491	0.8794	0.9378
No log	39.0	117	0.8645	0.4476	0.8645	0.9298
No log	40.0	120	0.8858	0.4431	0.8858	0.9411
No log	41.0	123	0.9276	0.4192	0.9276	0.9631

Framework versions

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