Version_Test_ASAP_FineTuningBERT_AugV14_k10_task1_organization_k10_k10_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: 0.7059
• Qwk: 0.6169
• Mse: 0.7060
• Rmse: 0.8403

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	7	5.6121	0.0616	5.6098	2.3685
No log	2.0	14	2.4621	0.0290	2.4601	1.5685
No log	3.0	21	1.1146	0.0	1.1131	1.0550
No log	4.0	28	0.9268	0.0518	0.9258	0.9622
No log	5.0	35	0.7784	0.3557	0.7773	0.8816
No log	6.0	42	0.7633	0.4115	0.7623	0.8731
No log	7.0	49	0.5587	0.5647	0.5580	0.7470
No log	8.0	56	0.7821	0.5200	0.7813	0.8839
No log	9.0	63	0.4913	0.6618	0.4909	0.7007
No log	10.0	70	0.4747	0.6340	0.4741	0.6885
No log	11.0	77	0.5096	0.6715	0.5093	0.7136
No log	12.0	84	0.5876	0.6538	0.5875	0.7665
No log	13.0	91	0.5266	0.6728	0.5264	0.7255
No log	14.0	98	0.5108	0.6134	0.5102	0.7143
No log	15.0	105	0.5589	0.6456	0.5588	0.7475
No log	16.0	112	0.5505	0.6112	0.5499	0.7416
No log	17.0	119	0.5948	0.6257	0.5943	0.7709
No log	18.0	126	0.8448	0.5696	0.8450	0.9192
No log	19.0	133	0.9808	0.5183	0.9812	0.9906
No log	20.0	140	1.1641	0.4694	1.1647	1.0792
No log	21.0	147	0.8094	0.5828	0.8096	0.8998
No log	22.0	154	0.5612	0.6496	0.5610	0.7490
No log	23.0	161	0.6263	0.6553	0.6262	0.7914
No log	24.0	168	0.5409	0.6670	0.5408	0.7354
No log	25.0	175	0.5971	0.6546	0.5970	0.7727
No log	26.0	182	0.7787	0.6067	0.7789	0.8825
No log	27.0	189	0.6775	0.6311	0.6775	0.8231
No log	28.0	196	0.5800	0.6415	0.5798	0.7614
No log	29.0	203	0.7138	0.6124	0.7139	0.8449
No log	30.0	210	0.5582	0.6278	0.5580	0.7470
No log	31.0	217	0.6497	0.6336	0.6497	0.8060
No log	32.0	224	0.5363	0.6552	0.5361	0.7322
No log	33.0	231	0.7059	0.6169	0.7060	0.8403

Framework versions

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