ASAP_FineTuningBERT_AugV6_k1_task1_organization_k1_k1_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: 0.8680
• Qwk: 0.4949
• Mse: 0.8680
• Rmse: 0.9316

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	12.8890	-0.0011	12.8890	3.5901
No log	2.0	4	9.9472	0.0018	9.9472	3.1539
No log	3.0	6	8.7139	0.0	8.7139	2.9519
No log	4.0	8	7.3810	0.0	7.3810	2.7168
No log	5.0	10	5.7643	0.0065	5.7643	2.4009
No log	6.0	12	4.3938	0.0079	4.3938	2.0961
No log	7.0	14	3.2416	0.0040	3.2416	1.8004
No log	8.0	16	2.4935	0.0230	2.4935	1.5791
No log	9.0	18	2.0364	0.0747	2.0364	1.4270
No log	10.0	20	1.6875	0.0518	1.6875	1.2990
No log	11.0	22	1.4080	0.0533	1.4080	1.1866
No log	12.0	24	1.0618	0.0316	1.0618	1.0304
No log	13.0	26	0.9812	0.0316	0.9812	0.9906
No log	14.0	28	1.0974	0.0316	1.0974	1.0475
No log	15.0	30	1.3938	0.0850	1.3938	1.1806
No log	16.0	32	1.2501	0.1064	1.2501	1.1181
No log	17.0	34	1.0616	0.1777	1.0616	1.0303
No log	18.0	36	1.1793	0.2216	1.1793	1.0859
No log	19.0	38	1.0778	0.3308	1.0778	1.0382
No log	20.0	40	1.1801	0.3898	1.1801	1.0863
No log	21.0	42	1.9151	0.2538	1.9151	1.3839
No log	22.0	44	1.5416	0.3298	1.5416	1.2416
No log	23.0	46	1.4745	0.3378	1.4745	1.2143
No log	24.0	48	0.8477	0.4446	0.8477	0.9207
No log	25.0	50	0.7671	0.4725	0.7671	0.8758
No log	26.0	52	1.3353	0.3428	1.3353	1.1556
No log	27.0	54	1.4812	0.3132	1.4812	1.2170
No log	28.0	56	0.9152	0.4389	0.9152	0.9567
No log	29.0	58	0.7235	0.5094	0.7235	0.8506
No log	30.0	60	0.7219	0.4935	0.7219	0.8497
No log	31.0	62	1.1388	0.3762	1.1388	1.0672
No log	32.0	64	1.0083	0.4257	1.0083	1.0041
No log	33.0	66	0.7755	0.4911	0.7755	0.8806
No log	34.0	68	0.8231	0.4779	0.8231	0.9073
No log	35.0	70	0.9423	0.4742	0.9423	0.9707
No log	36.0	72	0.9206	0.4719	0.9206	0.9595
No log	37.0	74	0.8846	0.4651	0.8846	0.9405
No log	38.0	76	0.9781	0.4241	0.9781	0.9890
No log	39.0	78	1.1599	0.4229	1.1599	1.0770
No log	40.0	80	0.9518	0.4437	0.9518	0.9756
No log	41.0	82	0.8629	0.4652	0.8629	0.9289
No log	42.0	84	0.8836	0.4625	0.8836	0.9400
No log	43.0	86	1.1953	0.4134	1.1953	1.0933
No log	44.0	88	0.9837	0.4446	0.9837	0.9918
No log	45.0	90	0.9300	0.4697	0.9300	0.9643
No log	46.0	92	1.0302	0.4278	1.0302	1.0150
No log	47.0	94	1.1905	0.4037	1.1905	1.0911
No log	48.0	96	0.9827	0.4597	0.9827	0.9913
No log	49.0	98	0.8680	0.4949	0.8680	0.9316

Framework versions

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