Version_weird_ASAP_FineTuningBERT_AugV12_k15_task1_organization_k15_k15_fold2

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: 0.6945
• Qwk: 0.5566
• Mse: 0.6937
• Rmse: 0.8329

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	7.7993	0.0	7.7994	2.7927
No log	2.0	6	6.0672	-0.0105	6.0675	2.4632
No log	3.0	9	4.7294	0.0039	4.7298	2.1748
No log	4.0	12	3.6024	0.0	3.6028	1.8981
No log	5.0	15	2.9609	0.0	2.9613	1.7209
No log	6.0	18	1.8841	0.0372	1.8845	1.3728
No log	7.0	21	1.3707	0.0213	1.3713	1.1710
No log	8.0	24	1.0405	0.0	1.0410	1.0203
No log	9.0	27	0.8036	0.1935	0.8041	0.8967
No log	10.0	30	0.8876	0.0430	0.8883	0.9425
No log	11.0	33	0.9652	0.0430	0.9655	0.9826
No log	12.0	36	1.2576	0.1787	1.2576	1.1214
No log	13.0	39	1.1862	0.2748	1.1856	1.0888
No log	14.0	42	0.7449	0.5012	0.7436	0.8623
No log	15.0	45	1.0230	0.4927	1.0215	1.0107
No log	16.0	48	1.1415	0.5073	1.1397	1.0676
No log	17.0	51	1.3904	0.4152	1.3892	1.1786
No log	18.0	54	0.8644	0.4930	0.8634	0.9292
No log	19.0	57	0.7616	0.5034	0.7610	0.8724
No log	20.0	60	0.7166	0.5264	0.7161	0.8462
No log	21.0	63	0.7784	0.5723	0.7776	0.8818
No log	22.0	66	0.6645	0.5860	0.6638	0.8147
No log	23.0	69	1.0177	0.5035	1.0165	1.0082
No log	24.0	72	1.0645	0.5064	1.0638	1.0314
No log	25.0	75	0.8246	0.5639	0.8238	0.9076
No log	26.0	78	0.6766	0.5803	0.6761	0.8223
No log	27.0	81	0.9101	0.4838	0.9093	0.9536
No log	28.0	84	0.8182	0.5247	0.8178	0.9043
No log	29.0	87	0.9458	0.5206	0.9448	0.9720
No log	30.0	90	0.8581	0.5327	0.8571	0.9258
No log	31.0	93	0.8886	0.5316	0.8875	0.9421
No log	32.0	96	0.7417	0.5457	0.7409	0.8608
No log	33.0	99	0.6724	0.5385	0.6718	0.8196
No log	34.0	102	0.6776	0.5511	0.6771	0.8229
No log	35.0	105	0.7152	0.5464	0.7145	0.8453
No log	36.0	108	0.6471	0.5677	0.6467	0.8042
No log	37.0	111	0.6907	0.5328	0.6900	0.8307
No log	38.0	114	0.8380	0.5105	0.8371	0.9149
No log	39.0	117	0.7164	0.5775	0.7159	0.8461
No log	40.0	120	0.7338	0.5472	0.7329	0.8561
No log	41.0	123	0.7218	0.5643	0.7209	0.8491
No log	42.0	126	0.6945	0.5566	0.6937	0.8329

Framework versions

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