Version_concise_ASAP_FineTuningBERT_AugV12_k1_task1_organization_k1_k1_fold0

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: 0.6598
• Qwk: 0.5736
• Mse: 0.6598
• Rmse: 0.8123

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	2	11.5529	0.0055	11.5529	3.3990
No log	2.0	4	9.4704	0.0	9.4704	3.0774
No log	3.0	6	7.5895	0.0	7.5895	2.7549
No log	4.0	8	5.9130	0.0472	5.9130	2.4317
No log	5.0	10	5.1158	0.0110	5.1158	2.2618
No log	6.0	12	3.7698	0.0039	3.7698	1.9416
No log	7.0	14	2.6405	0.0478	2.6405	1.6250
No log	8.0	16	1.9351	0.0538	1.9351	1.3911
No log	9.0	18	1.4629	0.0316	1.4629	1.2095
No log	10.0	20	1.4752	0.0316	1.4752	1.2146
No log	11.0	22	1.2365	0.0316	1.2365	1.1120
No log	12.0	24	1.1313	0.0316	1.1313	1.0636
No log	13.0	26	1.0640	0.0316	1.0640	1.0315
No log	14.0	28	1.0830	0.0487	1.0830	1.0407
No log	15.0	30	0.9791	0.0718	0.9791	0.9895
No log	16.0	32	1.1047	0.0928	1.1047	1.0511
No log	17.0	34	0.9156	0.1778	0.9156	0.9569
No log	18.0	36	0.6391	0.4836	0.6391	0.7994
No log	19.0	38	0.7379	0.3168	0.7379	0.8590
No log	20.0	40	0.8730	0.2701	0.8730	0.9344
No log	21.0	42	0.7774	0.4196	0.7774	0.8817
No log	22.0	44	0.5520	0.4868	0.5520	0.7430
No log	23.0	46	0.5726	0.4091	0.5726	0.7567
No log	24.0	48	0.5912	0.4778	0.5912	0.7689
No log	25.0	50	0.5544	0.5032	0.5544	0.7446
No log	26.0	52	0.5316	0.4718	0.5316	0.7291
No log	27.0	54	0.5302	0.4818	0.5302	0.7281
No log	28.0	56	0.5377	0.5397	0.5377	0.7333
No log	29.0	58	0.5687	0.5643	0.5687	0.7541
No log	30.0	60	0.5817	0.5875	0.5817	0.7627
No log	31.0	62	0.6247	0.5742	0.6247	0.7904
No log	32.0	64	0.7362	0.5307	0.7362	0.8580
No log	33.0	66	0.5917	0.6028	0.5917	0.7692
No log	34.0	68	0.7799	0.4881	0.7799	0.8831
No log	35.0	70	0.7614	0.4977	0.7614	0.8726
No log	36.0	72	0.6090	0.5636	0.6090	0.7804
No log	37.0	74	0.7372	0.5131	0.7372	0.8586
No log	38.0	76	0.7896	0.4906	0.7896	0.8886
No log	39.0	78	0.9483	0.4421	0.9483	0.9738
No log	40.0	80	0.7386	0.5205	0.7386	0.8594
No log	41.0	82	0.6317	0.5810	0.6317	0.7948
No log	42.0	84	0.7339	0.5645	0.7339	0.8567
No log	43.0	86	0.6883	0.5734	0.6883	0.8297
No log	44.0	88	0.6442	0.5718	0.6442	0.8026
No log	45.0	90	0.6427	0.5816	0.6427	0.8017
No log	46.0	92	0.9847	0.4921	0.9847	0.9923
No log	47.0	94	0.9873	0.4834	0.9873	0.9936
No log	48.0	96	0.6410	0.5596	0.6410	0.8006
No log	49.0	98	0.6275	0.5564	0.6275	0.7922
No log	50.0	100	0.7396	0.5338	0.7396	0.8600
No log	51.0	102	0.7818	0.5447	0.7818	0.8842
No log	52.0	104	0.6483	0.5825	0.6483	0.8052
No log	53.0	106	0.6598	0.5736	0.6598	0.8123

Framework versions

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