Version2ASAP_FineTuningBERT_AugV5_k3_task1_organization_k3_k3_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: 0.8527
• Qwk: 0.3823
• Mse: 0.8515
• Rmse: 0.9228

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	9.1206	-0.0002	9.1181	3.0196
No log	2.0	6	6.5485	0.0	6.5458	2.5585
No log	3.0	9	4.4043	0.0079	4.4022	2.0981
No log	4.0	12	3.1770	0.0	3.1751	1.7819
No log	5.0	15	2.0774	0.1120	2.0757	1.4407
No log	6.0	18	1.5622	0.0315	1.5607	1.2493
No log	7.0	21	1.3920	0.0583	1.3904	1.1792
No log	8.0	24	1.6223	0.0790	1.6206	1.2730
No log	9.0	27	1.0076	0.0211	1.0062	1.0031
No log	10.0	30	0.9702	0.0211	0.9689	0.9843
No log	11.0	33	1.4312	0.0856	1.4296	1.1957
No log	12.0	36	1.1502	0.0828	1.1488	1.0718
No log	13.0	39	0.8799	0.2341	0.8785	0.9373
No log	14.0	42	1.0959	0.1681	1.0944	1.0461
No log	15.0	45	0.8957	0.2638	0.8943	0.9457
No log	16.0	48	0.8882	0.2687	0.8868	0.9417
No log	17.0	51	1.0133	0.3040	1.0120	1.0060
No log	18.0	54	0.7554	0.3284	0.7542	0.8684
No log	19.0	57	0.7060	0.3695	0.7049	0.8396
No log	20.0	60	0.7074	0.3748	0.7063	0.8404
No log	21.0	63	0.6794	0.4409	0.6784	0.8236
No log	22.0	66	0.6825	0.4609	0.6815	0.8255
No log	23.0	69	0.8049	0.4331	0.8038	0.8966
No log	24.0	72	0.7366	0.5381	0.7356	0.8577
No log	25.0	75	0.7705	0.4386	0.7693	0.8771
No log	26.0	78	0.7560	0.4571	0.7547	0.8687
No log	27.0	81	0.7454	0.4848	0.7441	0.8626
No log	28.0	84	1.2343	0.2869	1.2324	1.1101
No log	29.0	87	0.8375	0.4205	0.8365	0.9146
No log	30.0	90	0.8645	0.4145	0.8636	0.9293
No log	31.0	93	1.1387	0.3079	1.1374	1.0665
No log	32.0	96	0.7779	0.4393	0.7772	0.8816
No log	33.0	99	0.7936	0.4204	0.7929	0.8904
No log	34.0	102	0.9459	0.3165	0.9447	0.9720
No log	35.0	105	0.8118	0.4023	0.8110	0.9006
No log	36.0	108	0.8076	0.4415	0.8067	0.8981
No log	37.0	111	0.8850	0.3697	0.8838	0.9401
No log	38.0	114	0.7676	0.4673	0.7666	0.8756
No log	39.0	117	0.8187	0.3907	0.8173	0.9041
No log	40.0	120	0.7564	0.4249	0.7553	0.8691
No log	41.0	123	0.7953	0.4309	0.7943	0.8912
No log	42.0	126	0.8235	0.4133	0.8224	0.9069
No log	43.0	129	0.7853	0.4595	0.7845	0.8857
No log	44.0	132	0.8527	0.3823	0.8515	0.9228

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0