Version3_ASAP_FineTuningBERT_AugV12_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: 1.3830
• Qwk: 0.3806
• Mse: 1.3830
• Rmse: 1.1760

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	11.1124	-0.0121	11.1124	3.3335
No log	2.0	4	10.1931	0.0018	10.1931	3.1927
No log	3.0	6	8.8145	0.0	8.8145	2.9689
No log	4.0	8	8.0698	0.0	8.0698	2.8407
No log	5.0	10	7.8313	0.0	7.8313	2.7984
No log	6.0	12	7.6419	0.0	7.6419	2.7644
No log	7.0	14	7.4386	0.0	7.4386	2.7274
No log	8.0	16	7.1972	0.0	7.1972	2.6828
No log	9.0	18	6.8721	0.0	6.8721	2.6215
No log	10.0	20	6.3363	0.0	6.3363	2.5172
No log	11.0	22	5.3480	0.0061	5.3480	2.3126
No log	12.0	24	4.0364	0.0079	4.0364	2.0091
No log	13.0	26	3.5051	0.0040	3.5051	1.8722
No log	14.0	28	2.7296	0.0040	2.7296	1.6521
No log	15.0	30	1.9342	0.0531	1.9342	1.3908
No log	16.0	32	1.5910	0.0331	1.5910	1.2613
No log	17.0	34	1.2803	0.0317	1.2803	1.1315
No log	18.0	36	1.1361	0.0317	1.1361	1.0659
No log	19.0	38	0.9506	0.1337	0.9506	0.9750
No log	20.0	40	0.9411	0.1861	0.9411	0.9701
No log	21.0	42	0.8730	0.2310	0.8730	0.9343
No log	22.0	44	0.8835	0.2143	0.8835	0.9400
No log	23.0	46	0.8870	0.2246	0.8870	0.9418
No log	24.0	48	0.9075	0.2385	0.9075	0.9527
No log	25.0	50	0.9203	0.2875	0.9203	0.9593
No log	26.0	52	0.9412	0.2470	0.9412	0.9702
No log	27.0	54	0.9338	0.3184	0.9338	0.9663
No log	28.0	56	1.0386	0.2807	1.0386	1.0191
No log	29.0	58	1.1482	0.3061	1.1482	1.0715
No log	30.0	60	1.0317	0.3613	1.0317	1.0158
No log	31.0	62	1.0118	0.3942	1.0118	1.0059
No log	32.0	64	1.1456	0.3317	1.1456	1.0703
No log	33.0	66	1.1345	0.3196	1.1345	1.0651
No log	34.0	68	1.1601	0.3670	1.1601	1.0771
No log	35.0	70	1.3330	0.3167	1.3330	1.1546
No log	36.0	72	1.3657	0.3260	1.3657	1.1686
No log	37.0	74	1.2961	0.3766	1.2961	1.1385
No log	38.0	76	1.4363	0.3091	1.4363	1.1985
No log	39.0	78	1.4064	0.2985	1.4064	1.1859
No log	40.0	80	1.3454	0.3556	1.3454	1.1599
No log	41.0	82	1.4272	0.3368	1.4272	1.1946
No log	42.0	84	1.4477	0.3561	1.4477	1.2032
No log	43.0	86	1.4441	0.3347	1.4441	1.2017
No log	44.0	88	1.3651	0.3643	1.3651	1.1684
No log	45.0	90	1.4164	0.3362	1.4164	1.1901
No log	46.0	92	1.4460	0.3419	1.4460	1.2025
No log	47.0	94	1.5767	0.3341	1.5767	1.2557
No log	48.0	96	1.5773	0.3565	1.5773	1.2559
No log	49.0	98	1.5403	0.3444	1.5403	1.2411
No log	50.0	100	1.4319	0.3561	1.4319	1.1966
No log	51.0	102	1.3830	0.3806	1.3830	1.1760

Framework versions

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