ASAP_FineTuningBERT_AugV6_k1_task1_organization_k1_k1_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: 1.1400
• Qwk: 0.3435
• Mse: 1.1407
• Rmse: 1.0680

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	13.0565	-0.0008	13.0545	3.6131
No log	2.0	4	8.8406	0.0	8.8389	2.9730
No log	3.0	6	6.7196	0.0	6.7180	2.5919
No log	4.0	8	6.5079	0.0	6.5063	2.5508
No log	5.0	10	6.3578	0.0	6.3563	2.5212
No log	6.0	12	6.1700	-0.0025	6.1685	2.4837
No log	7.0	14	5.8542	0.0	5.8528	2.4193
No log	8.0	16	5.3036	0.0	5.3023	2.3027
No log	9.0	18	4.6777	0.0	4.6764	2.1625
No log	10.0	20	4.0707	0.0	4.0695	2.0173
No log	11.0	22	3.6237	0.0	3.6226	1.9033
No log	12.0	24	3.1770	0.0	3.1760	1.7821
No log	13.0	26	2.5483	0.0502	2.5475	1.5961
No log	14.0	28	2.0388	0.0467	2.0379	1.4276
No log	15.0	30	1.8301	0.0834	1.8294	1.3525
No log	16.0	32	1.6908	0.0935	1.6902	1.3001
No log	17.0	34	1.1983	0.0355	1.1977	1.0944
No log	18.0	36	0.9742	0.0417	0.9737	0.9868
No log	19.0	38	0.9388	0.1501	0.9386	0.9688
No log	20.0	40	1.6981	0.1820	1.6976	1.3029
No log	21.0	42	1.4947	0.1864	1.4944	1.2224
No log	22.0	44	1.3656	0.1891	1.3655	1.1685
No log	23.0	46	2.1279	0.1492	2.1275	1.4586
No log	24.0	48	1.4069	0.2392	1.4070	1.1862
No log	25.0	50	0.7704	0.4551	0.7707	0.8779
No log	26.0	52	0.6943	0.5013	0.6944	0.8333
No log	27.0	54	0.7822	0.4244	0.7824	0.8845
No log	28.0	56	1.5110	0.2183	1.5110	1.2292
No log	29.0	58	2.7385	0.0593	2.7380	1.6547
No log	30.0	60	2.2825	0.1170	2.2823	1.5107
No log	31.0	62	1.0774	0.3487	1.0780	1.0383
No log	32.0	64	0.7726	0.4629	0.7732	0.8793
No log	33.0	66	1.0782	0.3837	1.0790	1.0388
No log	34.0	68	2.6649	0.0752	2.6650	1.6325
No log	35.0	70	3.2031	0.0376	3.2030	1.7897
No log	36.0	72	2.6177	0.0731	2.6180	1.6180
No log	37.0	74	1.4181	0.2922	1.4191	1.1913
No log	38.0	76	1.2087	0.3130	1.2098	1.0999
No log	39.0	78	1.8184	0.2183	1.8191	1.3487
No log	40.0	80	2.7934	0.0817	2.7931	1.6713
No log	41.0	82	2.8437	0.0819	2.8434	1.6862
No log	42.0	84	2.2865	0.1484	2.2871	1.5123
No log	43.0	86	1.7042	0.2239	1.7049	1.3057
No log	44.0	88	1.5346	0.2505	1.5355	1.2391
No log	45.0	90	1.5897	0.2319	1.5913	1.2615
No log	46.0	92	1.1400	0.3435	1.1407	1.0680

Framework versions

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