Version_concise_ASAP_FineTuningBERT_AugV12_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: 0.7156
• Qwk: 0.4258
• Mse: 0.7156
• Rmse: 0.8459

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	4	5.4433	0.0215	5.4433	2.3331
No log	2.0	8	3.5164	0.0115	3.5164	1.8752
No log	3.0	12	2.3214	0.0814	2.3214	1.5236
No log	4.0	16	1.6420	0.0715	1.6420	1.2814
No log	5.0	20	1.3122	0.0715	1.3122	1.1455
No log	6.0	24	1.0060	0.0715	1.0060	1.0030
No log	7.0	28	0.9773	0.0740	0.9773	0.9886
No log	8.0	32	0.7844	0.3747	0.7844	0.8857
No log	9.0	36	0.8878	0.1638	0.8878	0.9422
No log	10.0	40	0.7336	0.3868	0.7336	0.8565
No log	11.0	44	0.7075	0.4485	0.7075	0.8411
No log	12.0	48	0.9251	0.2404	0.9251	0.9618
No log	13.0	52	0.6808	0.3160	0.6808	0.8251
No log	14.0	56	0.7212	0.2869	0.7212	0.8492
No log	15.0	60	0.6632	0.4201	0.6632	0.8144
No log	16.0	64	0.8916	0.3794	0.8916	0.9443
No log	17.0	68	0.7707	0.4084	0.7707	0.8779
No log	18.0	72	0.7258	0.4709	0.7258	0.8519
No log	19.0	76	1.2653	0.2959	1.2653	1.1249
No log	20.0	80	0.8258	0.3629	0.8258	0.9088
No log	21.0	84	1.1472	0.2989	1.1472	1.0711
No log	22.0	88	0.7497	0.4276	0.7497	0.8659
No log	23.0	92	1.5718	0.2531	1.5718	1.2537
No log	24.0	96	1.1595	0.3632	1.1595	1.0768
No log	25.0	100	0.7114	0.4546	0.7114	0.8434
No log	26.0	104	1.3003	0.3146	1.3003	1.1403
No log	27.0	108	0.7131	0.3927	0.7131	0.8444
No log	28.0	112	1.1138	0.3867	1.1138	1.0554
No log	29.0	116	0.9330	0.4270	0.9330	0.9659
No log	30.0	120	0.6794	0.4610	0.6794	0.8242
No log	31.0	124	1.0947	0.3892	1.0947	1.0463
No log	32.0	128	0.7870	0.4462	0.7870	0.8871
No log	33.0	132	0.9038	0.4648	0.9038	0.9507
No log	34.0	136	0.8629	0.4385	0.8629	0.9289
No log	35.0	140	0.8491	0.4390	0.8491	0.9215
No log	36.0	144	0.8501	0.4481	0.8501	0.9220
No log	37.0	148	0.7431	0.4302	0.7431	0.8620
No log	38.0	152	0.7156	0.4258	0.7156	0.8459

Framework versions

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