ASAP_FineTuningBERT_AugV8_k7_task1_organization_k7_fold3

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: 0.9401
• Qwk: 0.4349
• Mse: 0.9405
• Rmse: 0.9698

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	6	6.4473	0.0013	6.4459	2.5389
No log	2.0	12	2.9316	0.0	2.9306	1.7119
No log	3.0	18	1.6729	0.0202	1.6722	1.2931
No log	4.0	24	1.4826	0.0302	1.4819	1.2173
No log	5.0	30	1.0210	0.0257	1.0205	1.0102
No log	6.0	36	0.7614	0.3613	0.7612	0.8725
No log	7.0	42	1.0831	0.2070	1.0831	1.0407
No log	8.0	48	0.7771	0.4473	0.7774	0.8817
No log	9.0	54	0.8992	0.3764	0.8998	0.9486
No log	10.0	60	0.9384	0.4197	0.9392	0.9691
No log	11.0	66	0.8380	0.4533	0.8387	0.9158
No log	12.0	72	0.7710	0.4648	0.7715	0.8784
No log	13.0	78	1.0001	0.3759	1.0005	1.0003
No log	14.0	84	0.9176	0.3775	0.9181	0.9582
No log	15.0	90	0.9640	0.3600	0.9643	0.9820
No log	16.0	96	0.9222	0.3729	0.9226	0.9605
No log	17.0	102	0.9674	0.3927	0.9677	0.9837
No log	18.0	108	0.9130	0.3984	0.9134	0.9557
No log	19.0	114	0.9812	0.4102	0.9817	0.9908
No log	20.0	120	0.8342	0.4375	0.8349	0.9137
No log	21.0	126	0.8097	0.4223	0.8104	0.9002
No log	22.0	132	0.9401	0.4349	0.9405	0.9698

Framework versions

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