Version_weird_ASAP_FineTuningBERT_AugV12_k15_task1_organization_k15_k15_fold4

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: 0.7061
• Qwk: 0.6293
• Mse: 0.7061
• 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	3	8.7056	0.0018	8.7056	2.9505
No log	2.0	6	5.5233	0.0282	5.5233	2.3502
No log	3.0	9	3.8615	0.0118	3.8615	1.9651
No log	4.0	12	2.6755	0.0040	2.6755	1.6357
No log	5.0	15	1.9193	0.0630	1.9193	1.3854
No log	6.0	18	1.3513	0.0420	1.3513	1.1625
No log	7.0	21	0.9800	0.0316	0.9800	0.9899
No log	8.0	24	0.8112	0.3128	0.8112	0.9007
No log	9.0	27	0.8531	0.0840	0.8531	0.9236
No log	10.0	30	0.8770	0.0840	0.8770	0.9365
No log	11.0	33	1.1533	0.0747	1.1533	1.0739
No log	12.0	36	0.9945	0.3138	0.9945	0.9972
No log	13.0	39	1.2626	0.2937	1.2626	1.1236
No log	14.0	42	0.7349	0.4895	0.7349	0.8573
No log	15.0	45	0.6135	0.5982	0.6135	0.7833
No log	16.0	48	0.6202	0.6307	0.6202	0.7875
No log	17.0	51	0.6593	0.6518	0.6593	0.8120
No log	18.0	54	0.6911	0.6522	0.6911	0.8313
No log	19.0	57	0.6560	0.6368	0.6560	0.8100
No log	20.0	60	1.1901	0.5374	1.1901	1.0909
No log	21.0	63	0.5996	0.6370	0.5996	0.7744
No log	22.0	66	1.0165	0.5740	1.0165	1.0082
No log	23.0	69	0.7451	0.6095	0.7451	0.8632
No log	24.0	72	0.7370	0.6279	0.7370	0.8585
No log	25.0	75	0.5880	0.6481	0.5880	0.7668
No log	26.0	78	1.4495	0.4660	1.4495	1.2040
No log	27.0	81	0.7022	0.6283	0.7022	0.8380
No log	28.0	84	0.6906	0.6456	0.6906	0.8310
No log	29.0	87	0.8017	0.6134	0.8017	0.8954
No log	30.0	90	0.6856	0.6124	0.6856	0.8280
No log	31.0	93	1.0612	0.5515	1.0612	1.0301
No log	32.0	96	0.6983	0.6316	0.6983	0.8356
No log	33.0	99	0.9102	0.6019	0.9102	0.9540
No log	34.0	102	0.6736	0.6513	0.6736	0.8207
No log	35.0	105	0.9061	0.5921	0.9061	0.9519
No log	36.0	108	0.6335	0.6506	0.6335	0.7959
No log	37.0	111	0.7401	0.6194	0.7401	0.8603
No log	38.0	114	0.7061	0.6293	0.7061	0.8403

Framework versions

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