ASAP_FineTuningBERT_AugV8_k4_task1_organization_k4_fold1

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: 0.9409
• Qwk: 0.4255
• Mse: 0.9404
• Rmse: 0.9697

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	9.1914	0.0	9.1887	3.0313
No log	2.0	8	5.2744	0.0516	5.2723	2.2961
No log	3.0	12	3.0349	0.0	3.0331	1.7416
No log	4.0	16	1.8506	0.0443	1.8490	1.3598
No log	5.0	20	1.4220	0.0106	1.4205	1.1919
No log	6.0	24	1.2095	0.0	1.2080	1.0991
No log	7.0	28	1.3558	0.0	1.3543	1.1638
No log	8.0	32	1.3549	0.0936	1.3534	1.1634
No log	9.0	36	1.5462	0.2067	1.5448	1.2429
No log	10.0	40	1.4052	0.1648	1.4038	1.1848
No log	11.0	44	1.0616	0.0894	1.0602	1.0296
No log	12.0	48	1.1559	0.1909	1.1545	1.0745
No log	13.0	52	0.8664	0.1734	0.8650	0.9300
No log	14.0	56	0.9360	0.4434	0.9346	0.9668
No log	15.0	60	0.9864	0.3798	0.9852	0.9926
No log	16.0	64	0.6976	0.4425	0.6963	0.8345
No log	17.0	68	0.8640	0.3992	0.8629	0.9289
No log	18.0	72	1.0769	0.3612	1.0759	1.0373
No log	19.0	76	0.7460	0.4248	0.7450	0.8631
No log	20.0	80	0.9205	0.4194	0.9195	0.9589
No log	21.0	84	0.7639	0.4833	0.7629	0.8734
No log	22.0	88	0.8827	0.4586	0.8817	0.9390
No log	23.0	92	0.9030	0.4213	0.9021	0.9498
No log	24.0	96	0.6090	0.5906	0.6081	0.7798
No log	25.0	100	1.2347	0.3832	1.2341	1.1109
No log	26.0	104	1.1580	0.3466	1.1580	1.0761
No log	27.0	108	1.0764	0.3813	1.0761	1.0374
No log	28.0	112	0.7062	0.5419	0.7056	0.8400
No log	29.0	116	0.8771	0.4302	0.8763	0.9361
No log	30.0	120	0.9126	0.3776	0.9121	0.9550
No log	31.0	124	0.8283	0.4584	0.8283	0.9101
No log	32.0	128	1.1315	0.3954	1.1309	1.0635
No log	33.0	132	0.8165	0.4895	0.8160	0.9033
No log	34.0	136	0.9409	0.4255	0.9404	0.9697

Framework versions

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